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. 31-GEMMASCOPE-RES-131K
    6. 43859
    Prev
    Next
    INDEX
    Explanations

    technical terms and parameters related to transmission characteristics in communication systems

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

    channel signal loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.54
     jsPsych
    -0.52
     GenerationType
    -0.51
    IntoConstraints
    -0.50
    Населення
    -0.47
     مرئيه
    -0.44
    httphttps
    -0.43
    ::::::::
    -0.43
    Personensuche
    -0.43
    DotNetBar
    -0.43
    POSITIVE LOGITS
     attenuation
    0.63
     deterioration
    0.56
     loss
    0.56
     propagation
    0.56
     degradation
    0.55
     transmission
    0.54
     impairments
    0.54
     impairment
    0.50
     losses
    0.50
    atten
    0.50
    Activations Density 0.168%

    No Known Activations