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
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 14232
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to fixed structures or frameworks in various contexts

    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
     mergeFrom
    -0.47
    SourceChecksum
    -0.43
    पया
    -0.42
    endpush
    -0.40
     uLocal
    -0.40
    CodeDom
    -0.40
    CppMethod
    -0.39
    anson
    -0.39
     Lor
    -0.39
     DataTypes
    -0.39
    POSITIVE LOGITS
     Fix
    0.98
     fix
    0.93
     Fixed
    0.91
    Fix
    0.91
    Fixed
    0.89
     FIX
    0.87
     fixing
    0.85
     fixes
    0.84
    fix
    0.83
     Fixing
    0.83
    Activations Density 0.174%

    No Known Activations