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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 24-GEMMASCOPE-RES-131K
    6. 1219
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and file structures

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

    object evolution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     utafitiHapana
    -0.40
     CURIAM
    -0.36
    arot
    -0.36
     Meksiku
    -0.35
    ToTop
    -0.35
     band
    -0.34
    getNew
    -0.32
     Band
    -0.31
    unref
    -0.31
     kant
    -0.31
    POSITIVE LOGITS
    styleUrls
    0.79
     useStyles
    0.67
     invokingState
    0.66
     makeStyles
    0.59
    +#+#
    0.52
     Administrativna
    0.52
    Styling
    0.52
    StyleSheet
    0.50
     StyleSheet
    0.49
    AttributeSet
    0.49
    Activations Density 0.001%

    No Known Activations