© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15359
    Prev
    Next
    INDEX
    Explanations

    json-like structure elements or syntax

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

    Tokens before square brackets

    np_acts-logits-general · gemini-2.0-flash

    structured text punctuation

    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
    <eos>
    -0.92
    ↵↵
    -0.79
    !
    -0.64
    ?
    -0.61
    ↵↵↵
    -0.59
    ,
    -0.58
    ↵↵↵↵
    -0.56
    .</
    -0.54
    .
    -0.52
    .
    -0.50
    POSITIVE LOGITS
     للمعارف
    1.16
    MigrationBuilder
    1.11
    UnknownFieldSet
    0.93
     الحره
    0.85
    Autoritní
    0.85
    AddTagHelper
    0.84
    tagHelperRunner
    0.81
     myſelf
    0.79
    出版年
    0.78
    errHandler
    0.77
    Activations Density 0.279%

    No Known Activations