© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9452
    Prev
    Next
    INDEX
    Explanations

    specific high-activation metrics or measurements related to data or qualitative assessments

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

    HTML tags and code-related words

    np_acts-logits-general · gemini-2.0-flash

    salisbury, below, are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/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.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     protoimpl
    -0.76
    Personensuche
    -0.74
     يتيمه
    -0.72
    OGND
    -0.70
     виправивши
    -0.69
    afficheront
    -0.68
    ########.
    -0.63
     @"/
    -0.63
     WaitForSeconds
    -0.60
     ProtoMessage
    -0.60
    POSITIVE LOGITS
    Tags
    0.40
    Yours
    0.34
     EconPapers
    0.33
    にほんブログ村
    0.32
    Nice
    0.32
    <h1>
    0.31
     Tags
    0.30
    glLoadIdentity
    0.30
    さて
    0.29
    المصدر
    0.29
    Activations Density 0.409%

    No Known Activations