© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-131K
    11. 10584
    Prev
    Next
    INDEX
    Explanations

    conditional statements in the code, particularly 'if' and 'while' statements

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

    if conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     betweenstory
    -0.69
     _('
    -0.57
    (__('
    -0.55
     _("
    -0.50
     uLocal
    -0.49
     cq
    -0.47
     CRI
    -0.45
     becoming
    -0.44
     OMITBAD
    -0.43
     __('
    -0.42
    POSITIVE LOGITS
    if
    1.10
    elif
    0.69
     If
    0.65
     jestli
    0.65
    If
    0.64
     eğer
    0.64
     Jeśli
    0.61
     if
    0.60
     TÉCN
    0.60
    Jeśli
    0.58
    Activations Density 0.046%

    No Known Activations