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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4187
    Prev
    Next
    INDEX
    Explanations

    statements related to error logging and handling

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

    Code or commands followed by error messages

    np_acts-logits-general · gemini-2.0-flash

    console logging

    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
     ExecuteAsync
    -0.71
    省市镇
    -0.65
    OGND
    -0.63
     Taktlose
    -0.62
     Савезне
    -0.60
     JpaRepository
    -0.60
     oprot
    -0.60
    دانشنامهٔ
    -0.59
    antası
    -0.58
    AnchorStyles
    -0.57
    POSITIVE LOGITS
     bahía
    0.34
     auquel
    0.33
     pérdida
    0.33
     catedral
    0.33
    CrossRef
    0.32
     Producción
    0.31
     herido
    0.31
     تضيفلها
    0.31
     optar
    0.31
     perda
    0.30
    Activations Density 0.092%

    No Known Activations