© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 85000
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to conditional checks and empty value verification

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

    isinstance or CURIAM

    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
     AssemblyCulture
    -0.59
     "..\..\..\
    -0.56
    RTEX
    -0.53
    Dens
    -0.51
    XtraGrid
    -0.51
    StatusOK
    -0.49
     "..\..\
    -0.49
    Vidite
    -0.49
    ngrx
    -0.49
     colar
    -0.49
    POSITIVE LOGITS
    IsNullOrEmpty
    1.36
    TryParse
    0.56
    TryGetValue
    0.50
    setattr
    0.49
    abestanden
    0.48
     CURIAM
    0.47
     propOrder
    0.46
     isinstance
    0.44
     nahilalakip
    0.44
     isset
    0.43
    Activations Density 0.001%

    No Known Activations