© 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. 12-GEMMASCOPE-RES-16K
    11. 2505
    Prev
    Next
    INDEX
    Explanations

    components and properties related to data structures or programming constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     snippetHide
    -0.73
    tagHelperRunner
    -0.69
     protoimpl
    -0.69
    enumii
    -0.67
     HasFactory
    -0.66
     Reſ
    -0.65
     Verſ
    -0.65
    iffance
    -0.64
     témoig
    -0.64
    脚注の使い方
    -0.63
    POSITIVE LOGITS
    Попис
    0.30
    toJSONString
    0.30
    shadowColor
    0.30
    ForRow
    0.29
     /
    0.29
    anInt
    0.29
    strncpy
    0.27
    NSArray
    0.26
    devtool
    0.26
     мәкал
    0.25
    Activations Density 1.195%

    No Known Activations