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
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 844
    Prev
    Next
    INDEX
    Explanations

    technical terms related to file handling and module resolution in programming

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

    file paths and path resolution operations.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    EDEFAULT
    -0.59
    adaptiveStyles
    -0.59
    OGND
    -0.56
    fillType
    -0.56
    :✨
    -0.55
    transQ
    -0.54
    <?
    -0.52
    crollView
    -0.52
    VYMaps
    -0.50
     surla
    -0.50
    POSITIVE LOGITS
     join
    0.55
    join
    0.53
     Join
    0.50
    Join
    0.50
     joins
    0.48
     os
    0.47
     joining
    0.46
     Path
    0.44
     Joins
    0.41
     JOIN
    0.40
    Activations Density 0.181%

    No Known Activations