© 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. 20-GEMMASCOPE-RES-16K
    11. 6211
    Prev
    Next
    INDEX
    Explanations

    references to data structures, their attributes, and interactions in code

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

    programming-related terms and code structures, particularly from database and software development contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -1.09
    XmlAccessType
    -1.00
     resourceCulture
    -0.99
    principalTable
    -0.97
    tagHelperRunner
    -0.97
    AnchorStyles
    -0.96
    MigrationBuilder
    -0.95
    Diweddarwch
    -0.94
    +#+#
    -0.94
     للاسماء
    -0.91
    POSITIVE LOGITS
     par
    0.33
    -
    0.31
    半
    0.29
     régime
    0.29
    人
    0.27
     coti
    0.27
     سامسون
    0.27
     semi
    0.27
    ENODEV
    0.27
    PAR
    0.26
    Activations Density 1.035%

    No Known Activations