© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 10503
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to parole and sentencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DE
    -0.86
    CO
    -0.83
    CA
    -0.76
    RE
    -0.75
    NE
    -0.74
    MA
    -0.74
    BE
    -0.73
    SE
    -0.72
    ME
    -0.72
    LE
    -0.71
    POSITIVE LOGITS
     Si
    1.14
     Lo
    1.14
     Ha
    1.12
     Mi
    1.11
     Mo
    1.10
     Da
    1.09
     Se
    1.08
     Te
    1.08
     Ro
    1.08
     Po
    1.08
    Activations Density 0.529%

    No Known Activations