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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1888
    Prev
    Next
    INDEX
    Explanations

    placeholders or markers that signify sections or structures in a codebase

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

    nginx control flow

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    AddHtmlAttribute
    -0.55
     виправивши
    -0.48
    bindingNavigator
    -0.45
    UnitTesting
    -0.44
     AssemblyTitle
    -0.43
    XMLSchema
    -0.41
    BeginContext
    -0.41
     snippetHide
    -0.41
     iprot
    -0.40
    astéroïdes
    -0.39
    POSITIVE LOGITS
    IContainer
    0.77
    তথ্যসূত্র
    0.53
     Infór
    0.49
    /**
    0.47
     sahiptir
    0.44
    mtrl
    0.44
    íritu
    0.42
     librement
    0.41
     beginnetje
    0.41
     hidupnya
    0.41
    Activations Density 0.002%

    No Known Activations