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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8989
    Prev
    Next
    INDEX
    Explanations

    references to plans or strategies in various contexts

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

    "plan" (or its variations)

    np_acts-logits-general · gemini-2.0-flash

    the word plan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sesama
    -0.49
     médicale
    -0.47
     suprême
    -0.45
     ujednoznacz
    -0.45
     female
    -0.44
    𝟴
    -0.44
     resourceCulture
    -0.42
    <bos>
    -0.42
    aigu
    -0.41
     Gött
    -0.41
    POSITIVE LOGITS
     plan
    2.38
    plan
    2.16
    Plan
    2.11
     Plan
    2.09
     plans
    1.98
     Plans
    1.95
    Plans
    1.93
     PLAN
    1.88
    plans
    1.88
     PLANS
    1.76
    Activations Density 0.078%

    No Known Activations