© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10574
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Plan" and its variations, indicating a focus on strategic or operational initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "plan" in various contexts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    the word "Plan" (often as part of "Planck" in scientific contexts or as a standalone word meaning a proposed course of action).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    words containing the substring “plan” (any case), whether standalone or embedded in longer words and names.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    󠁴
    -0.57
    kenstock
    -0.43
     Italijanski
    -0.41
    الدراسه
    -0.40
    ding
    -0.38
     לכ
    -0.36
     CB
    -0.34
     relatively
    -0.34
     tur
    -0.33
    icamente
    -0.33
    POSITIVE LOGITS
    Plan
    0.63
     Plan
    0.63
    protoimpl
    0.62
     PLAN
    0.57
    plan
    0.57
     plan
    0.57
     ContentValues
    0.55
    RTCF
    0.53
     IndexPath
    0.53
     estratégico
    0.52
    Activations Density 0.178%

    No Known Activations