© 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. 18-GEMMASCOPE-RES-16K
    11. 11191
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols in the text

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

    Code, paths, or identifiers

    np_acts-logits-general · gemini-2.0-flash

    strategy key generated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sir
    -0.53
    <eos>
    -0.51
     e
    -0.50
    .”
    -0.49
     planning
    -0.45
     …
    -0.44
    ForResult
    -0.44
     A
    -0.44
    ↵↵
    -0.44
    oe
    -0.44
    POSITIVE LOGITS
    expandindo
    0.92
     houſe
    0.86
    ArgsConstructor
    0.81
     itſelf
    0.81
    AndEndTag
    0.78
     Roskov
    0.77
     Majefty
    0.77
     ―――――
    0.77
    CppMethod
    0.75
    //
    0.75
    Activations Density 0.024%

    No Known Activations