© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 4739
    Prev
    Next
    INDEX
    Explanations

    incidents involving escapes or attempts to evade law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متحده
    -0.51
     Pollut
    -0.50
    StringVar
    -0.49
    reci
    -0.48
     Wikimedijinoj
    -0.47
     externi
    -0.47
    STROKE
    -0.47
    WebMethod
    -0.47
    ichio
    -0.45
     Obtén
    -0.44
    POSITIVE LOGITS
     escape
    1.71
     flee
    1.61
     fleeing
    1.61
     escaping
    1.57
     escapes
    1.50
     hiding
    1.46
     escaped
    1.43
    escape
    1.38
     Hiding
    1.32
     evade
    1.31
    Activations Density 0.442%

    No Known Activations