© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 99745
    Prev
    Next
    INDEX
    Explanations

    patterns or structures in data and their associated methodologies or findings

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

    citations and numeric data

    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
    tableFuture
    -0.66
     MainAxisSize
    -0.54
    rungsseite
    -0.52
     nahilalakip
    -0.49
    interopRequire
    -0.49
    ThroughAttribute
    -0.48
    enciaga
    -0.46
    ArgumentParser
    -0.46
    FailureListener
    -0.45
     autorytatywna
    -0.44
    POSITIVE LOGITS
     betweenstory
    0.41
    цездатний
    0.39
    хьтан
    0.39
    клопе
    0.39
    StructEnd
    0.39
     EClass
    0.36
    เท
    0.36
    XmlIgnore
    0.35
     formative
    0.35
     égal
    0.35
    Activations Density 0.066%

    No Known Activations