© 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. 0-GEMMASCOPE-RES-16K
    6. 3118
    Prev
    Next
    INDEX
    Explanations

    references to victims, particularly in contexts involving crime and justice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    evos
    -0.54
    EndInit
    -0.52
    glBind
    -0.51
    larry
    -0.49
    Endor
    -0.49
     Monty
    -0.49
     grat
    -0.48
    InSection
    -0.48
    Solar
    -0.48
     srs
    -0.48
    POSITIVE LOGITS
     victim
    0.66
    itinéraire
    0.60
    Integer
    0.52
     Victim
    0.49
     victims
    0.47
    victim
    0.46
    tle
    0.46
    Victim
    0.45
     journal
    0.43
    BASEPATH
    0.43
    Activations Density 0.194%

    No Known Activations