Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 82047
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming languages

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

    initiates 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 @ 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
    MockBean
    -0.68
     bénévol
    -0.63
    aspetto
    -0.49
    reza
    -0.47
    attenzione
    -0.46
    accompag
    -0.46
    alu
    -0.45
    ypen
    -0.45
    zou
    -0.45
    tahankan
    -0.45
    POSITIVE LOGITS
     if
    1.15
     IF
    1.05
    if
    1.03
     If
    1.01
    If
    0.97
     ifs
    0.89
    IF
    0.84
    ifs
    0.83
     jika
    0.72
     Если
    0.71
    Activations Density 0.030%

    No Known Activations