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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-131K
    6. 75219
    Prev
    Next
    INDEX
    Explanations

    programming constructs and object-related keywords

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

    historys, Next Results, Script, shadowCoord

    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
     Administrativna
    -0.87
     Савезне
    -0.77
    ſſung
    -0.72
     zuſammen
    -0.70
    <unused41>
    -0.69
    <pad>
    -0.69
    <unused28>
    -0.69
    <unused68>
    -0.69
    <unused16>
    -0.69
    <unused8>
    -0.69
    POSITIVE LOGITS
    ="#">
    0.26
     çift
    0.22
    ">"
    0.21
     millas
    0.21
     disfraces
    0.20
     nincs
    0.20
    ...
    0.20
     péché
    0.20
    ="">
    0.20
     espèce
    0.20
    Activations Density 0.011%

    No Known Activations