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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 20280
    Prev
    Next
    INDEX
    Explanations

    punctuation and function-related syntax in programming code

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

    movie initializer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.76
    SourceChecksum
    -0.57
     disambiguazione
    -0.56
     betweenstory
    -0.55
    iſchen
    -0.52
    deutig
    -0.52
    niſſe
    -0.50
     yyb
    -0.50
    UserScript
    -0.50
    SOUNDBITE
    -0.50
    POSITIVE LOGITS
     HasFactory
    0.48
    GenerationType
    0.42
    WarningLevel
    0.36
     numberOfRows
    0.35
    Rujuakan
    0.34
     "..\..\
    0.33
    EntityFramework
    0.31
    quelize
    0.30
     declarado
    0.30
     SwiftUI
    0.30
    Activations Density 0.001%

    No Known Activations