© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4493
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to variable assignments and property setting

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

    Code and programming syntax

    np_acts-logits-general · gemini-2.0-flash

    setting variable or processing parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Greet
    -0.35
     orologio
    -0.35
    getattr
    -0.33
     gratified
    -0.32
     Mitglieder
    -0.31
     anomalous
    -0.31
    みよう
    -0.31
     Editorial
    -0.31
     Alde
    -0.31
    remadura
    -0.31
    POSITIVE LOGITS
    ⓧ
    0.66
    AddTagHelper
    0.60
    脚注の使い方
    0.58
    paramref
    0.57
    findpost
    0.56
     supplied
    0.53
    IBOutlet
    0.53
     parameter
    0.53
    providedIn
    0.52
    nodoc
    0.52
    Activations Density 0.735%

    No Known Activations