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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120274
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to function definitions and execution in code

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

    program entry points

    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
    fjspx
    -0.66
    PickerController
    -0.63
    évaluateur
    -0.62
    protoimpl
    -0.62
    styleType
    -0.61
     disambiguazione
    -0.60
    OGND
    -0.59
    ValueStyle
    -0.58
    elemField
    -0.57
     שוליים
    -0.56
    POSITIVE LOGITS
     coordinación
    0.35
     direzione
    0.33
     calificación
    0.32
     resistencia
    0.32
     confronti
    0.31
     impianti
    0.31
     morire
    0.31
    afterEach
    0.31
     garantía
    0.31
     finalidad
    0.31
    Activations Density 0.007%

    No Known Activations