© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 8037
    Prev
    Next
    INDEX
    Explanations

    code-related components and structures in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aislado
    -0.40
     aislados
    -0.34
     práctico
    -0.33
     agencias
    -0.32
     débil
    -0.32
     obligado
    -0.32
     regulación
    -0.31
     organizado
    -0.30
     vuestros
    -0.29
     mínimos
    -0.29
    POSITIVE LOGITS
    MigrationBuilder
    0.71
    tagHelperRunner
    0.69
    Activated
    0.69
    XtraReports
    0.67
    IVEREF
    0.66
    RefNanny
    0.66
    MessageTagHelper
    0.65
     Router
    0.65
    yntaxException
    0.63
     ActivatedRoute
    0.63
    Activations Density 0.148%

    No Known Activations