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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9027
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts, failures, and discussions about social or political issues

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

    sequences describing failed attempts or unsuccessful efforts to achieve a goal.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
     wireType
    -0.33
     tamb
    -0.32
     ого
    -0.29
    restriction
    -0.29
     cher
    -0.28
    uger
    -0.28
     dol
    -0.27
     segreg
    -0.27
     netto
    -0.27
     skak
    -0.27
    POSITIVE LOGITS
     failed
    2.81
     failure
    2.53
     fail
    2.42
     unsuccessful
    2.39
     fails
    2.34
    failed
    2.34
     failing
    2.30
     failures
    2.28
     Failed
    2.25
     Failure
    2.22
    Activations Density 1.327%

    No Known Activations