© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1657
    Prev
    Next
    INDEX
    Explanations

    specific coding structures and attributes in web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strijden
    -0.44
    ApiModel
    -0.43
    ImageContext
    -0.43
    Bioaccumulative
    -0.41
    ziehungen
    -0.41
     šal
    -0.40
    ########.
    -0.40
     שוליים
    -0.40
     verstanden
    -0.40
     TAMBÉM
    -0.39
    POSITIVE LOGITS
    WebControls
    1.77
    IsPostBack
    0.93
    vaadin
    0.82
    DataBind
    0.73
    fjspx
    0.70
    
    0.56
    HtmlAttribute
    0.56
    wicket
    0.56
    InitVars
    0.53
    migrationBuilder
    0.53
    Activations Density 0.111%

    No Known Activations