© 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. 9-GEMMASCOPE-RES-16K
    6. 9028
    Prev
    Next
    INDEX
    Explanations

    instances of bolded text elements in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    帖最后由
    -0.72
     ویکی‌پدی
    -0.59
    DIPSETTING
    -0.59
    -------------</
    -0.57
    ---*/
    -0.56
    点此举报
    -0.56
    AddTagHelper
    -0.56
    DebuggerNonUser
    -0.51
     Picchu
    -0.51
    loài
    -0.49
    POSITIVE LOGITS
    </strong>
    1.11
    </b>
    0.91
    )");
    
    0.63
     itſelf
    0.61
    ')")
    0.60
    )');
    0.57
     ſche
    0.57
    ſelf
    0.55
    GetHashCode
    0.55
    gaard
    0.52
    Activations Density 0.048%

    No Known Activations