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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 43381
    Prev
    Next
    INDEX
    Explanations

    names and email addresses linked to academic or professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sections with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    <bos>
    -0.28
    XmlAccessType
    -0.26
     tend
    -0.25
     become
    -0.24
     .
    -0.24
    CodedInputStream
    -0.24
     dis
    -0.23
     disp
    -0.23
     basically
    -0.23
     si
    -0.23
    POSITIVE LOGITS
    帖最后由
    0.71
     kasarigan
    0.70
     Administrativna
    0.69
    ſelben
    0.65
    fromnode
    0.63
    XmlAccessorType
    0.63
     nonUne
    0.63
    RefNanny
    0.62
     lentejuelas
    0.62
     utafitiHapana
    0.61
    Activations Density 0.058%

    No Known Activations