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

    Neuronpedia

    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. 20-GEMMASCOPE-RES-16K
    11. 9012
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific initial marker or header in the document

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

    Tokens preceding questions or requests for help

    np_acts-logits-general · gemini-2.0-flash

    question or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.83
     Administrativna
    -0.69
    FontOfSize
    -0.67
    igshid
    -0.66
    ".
    -0.66
     تانيه
    -0.65
     Anſ
    -0.65
    OGND
    -0.65
    ']>;
    -0.65
     Estatal
    -0.64
    POSITIVE LOGITS
    .
    0.69
     _
    0.59
     my
    0.58
     et
    0.54
    []
    0.54
     self
    0.52
    ?
    0.52
    ,
    0.51
     user
    0.51
     a
    0.50
    Activations Density 0.122%

    No Known Activations