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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 12219
    Prev
    Next
    INDEX
    Explanations

    scientific terms and data related to health conditions, particularly focusing on obesity and environmental factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnchorStyles
    -0.59
    queryInterface
    -0.53
    wieś
    -0.50
    ochim
    -0.50
     increí
    -0.50
     مرئيه
    -0.49
    $_['
    -0.45
     utafitiHapana
    -0.44
     跳转至
    -0.44
    を起こ
    -0.44
    POSITIVE LOGITS
    principalColumn
    0.42
     moeili
    0.40
     difficulties
    0.40
     problém
    0.36
    InputBorder
    0.35
     BIBSYS
    0.34
     moeilijk
    0.34
     difficult
    0.34
     situations
    0.34
     dific
    0.33
    Activations Density 0.609%

    No Known Activations