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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7148
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical data structure elements and their properties in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insuffisamment
    -0.42
    AssignableFrom
    -0.38
     Krieges
    -0.38
    multicolumn
    -0.36
     occurred
    -0.36
    MessageTagHelper
    -0.36
     estekak
    -0.35
     Tracy
    -0.34
    krie
    -0.34
    チャート
    -0.34
    POSITIVE LOGITS
    ArgsConstructor
    0.72
     surla
    0.64
     propOrder
    0.61
     BoxDecoration
    0.61
    SequentialGroup
    0.59
     initWith
    0.58
    الدراسه
    0.57
    EDEFAULT
    0.57
    CGRectMake
    0.54
     initWithFrame
    0.54
    Activations Density 0.225%

    No Known Activations