Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14950
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their opinions or personal experiences

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

    Text after bracketed material

    np_acts-logits-general · gemini-2.0-flash

    legal and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     للمعارف
    -0.69
     nahilalakip
    -0.63
    AccessorTable
    -0.62
    ValueStyle
    -0.59
     وتسجيلات
    -0.58
    IUrlHelper
    -0.57
     समीक्षाओं
    -0.55
    AutoScaleMode
    -0.55
     Signalez
    -0.55
    matchCondition
    -0.55
    POSITIVE LOGITS
     aš
    0.39
    MigrationBuilder
    0.32
     IFTT
    0.31
     plais
    0.30
     alivio
    0.30
    PropertyChanged
    0.30
     lemari
    0.29
    Voci
    0.29
     tæn
    0.29
     listos
    0.29
    Activations Density 0.493%

    No Known Activations