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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 12814
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts, particularly those associated with code functions, declarations, and conditions involving data handling and memory management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobal
    -0.36
    RelativeLayout
    -0.33
    sendRedirect
    -0.33
    AppCompatTheme
    -0.32
    UnitTesting
    -0.31
    InternalFrame
    -0.29
     instruct
    -0.29
     erstmal
    -0.28
     recommandations
    -0.28
    stdc
    -0.28
    POSITIVE LOGITS
     يتيمه
    1.18
    Cyfarwyddwr
    0.93
     فريبيس
    0.91
    EDEFAULT
    0.91
    tagHelperRunner
    0.88
    EndGlobalSection
    0.87
    Географиясе
    0.87
    Jeografia
    0.86
     мәкал
    0.82
    hyrchwyd
    0.81
    Activations Density 1.327%

    No Known Activations