© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 51940
    Prev
    Next
    INDEX
    Explanations

    various programming-related keywords, particularly those associated with imports and packages

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

    code organization structure

    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
     her
    -0.35
     especially
    -0.34
    her
    -0.31
     Interactive
    -0.29
     особенно
    -0.29
     S
    -0.28
     (
    -0.27
     \&
    -0.27
    :
    -0.27
     ideal
    -0.26
    POSITIVE LOGITS
     autorytatywna
    0.96
    delwed
    0.90
     $_"
    0.88
     CreateTagHelper
    0.81
    principalColumn
    0.80
    dafx
    0.79
    帖最后由
    0.78
    хьтан
    0.75
    DotNetBar
    0.74
     PeEnEo
    0.73
    Activations Density 0.045%

    No Known Activations