© 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. 3-GEMMASCOPE-RES-16K
    6. 11420
    Prev
    Next
    INDEX
    Explanations

    words related to demonstration and proof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.66
    rosas
    -0.64
     Biscuits
    -0.63
     philosophi
    -0.62
    INTA
    -0.62
     biscuits
    -0.60
     Ast
    -0.59
     isometric
    -0.59
    ····
    -0.58
     Wro
    -0.58
    POSITIVE LOGITS
     mold
    1.19
     mould
    1.02
     Mold
    0.96
    mold
    0.96
     molds
    0.95
     devil
    0.94
    Mold
    0.89
    devil
    0.87
     Devil
    0.85
    protoimpl
    0.83
    Activations Density 0.122%

    No Known Activations