© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 801
    Prev
    Next
    INDEX
    Explanations

    details related to authorship or contributions in academic references

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

    References with a comma followed by a letter

    np_acts-logits-general · gemini-2.0-flash

    citations with commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.81
     $_"
    -0.77
     $_(
    -0.70
    󠁣
    -0.69
     ModelExpression
    -0.66
    toHaveBeen
    -0.66
     Normdatei
    -0.66
     resourceCulture
    -0.65
    synthesize
    -0.64
    TypedDataSet
    -0.64
    POSITIVE LOGITS
     meia
    0.31
     calcetines
    0.27
     najdete
    0.26
    fclose
    0.26
     comigo
    0.26
    ÍAS
    0.26
     Púb
    0.24
     demandes
    0.24
     consultez
    0.23
     Consultez
    0.23
    Activations Density 0.253%

    No Known Activations