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. 20-GEMMASCOPE-RES-16K
    6. 425
    Prev
    Next
    INDEX
    Explanations

    temperature and elevation values in scientific contexts

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

    scientific notation and detailed numerical measurements, particularly related to chemical or experimental data.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Personensuche
    -0.65
     للمعارف
    -0.63
    AutoScaleMode
    -0.60
    AndEndTag
    -0.59
     Wikimedijinoj
    -0.58
     незавершена
    -0.57
     Chwiliwch
    -0.57
     Biôgrafia
    -0.53
    localctx
    -0.53
    uxxxx
    -0.53
    POSITIVE LOGITS
     dismin
    0.33
    뀔
    0.32
    WithMany
    0.31
     samti
    0.30
    GEBURTS
    0.30
     dieux
    0.30
     rayas
    0.29
     onCreateView
    0.29
    bebasan
    0.29
    glected
    0.28
    Activations Density 0.537%

    No Known Activations