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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2379
    Prev
    Next
    INDEX
    Explanations

    numerical data or measurements associated with phase differences and torque in mechanical or electrical systems

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

    "90" (likely degrees or similar angles)

    np_acts-logits-general · gemini-2.0-flash

    angles, degrees, days, periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.64
    tagHelperRunner
    -0.56
    :"-"`
    -0.53
     Samuels
    -0.50
    Daz
    -0.49
    CopyWith
    -0.49
     ditem
    -0.49
    esar
    -0.49
     باسم
    -0.48
     fün
    -0.47
    POSITIVE LOGITS
    Sharper
    0.53
    Jeografia
    0.47
    րջ
    0.47
    Holes
    0.47
    ześnie
    0.46
    stdc
    0.46
    igers
    0.46
     môn
    0.45
     sposa
    0.44
    farin
    0.44
    Activations Density 0.367%

    No Known Activations