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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 92407
    Prev
    Next
    INDEX
    Explanations

    terms related to confounding variables and statistical terms associated with findings

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

    words starting with conf

    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
    AnimationsModule
    -0.64
    QMetaType
    -0.61
    RectangleBorder
    -0.61
     chré
    -0.59
     vété
    -0.59
    WebVitals
    -0.58
     MainAxisSize
    -0.57
     pitié
    -0.57
     esternos
    -0.56
    ThroughAttribute
    -0.55
    POSITIVE LOGITS
     conf
    2.06
     Conf
    1.91
    Conf
    1.83
    conf
    1.77
     CONF
    1.59
    CONF
    1.41
     Confessions
    1.17
     confocal
    1.05
     Confession
    1.03
     confession
    0.99
    Activations Density 0.016%

    No Known Activations