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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 157
    Prev
    Next
    INDEX
    Explanations

    specific actions, processes, or conditions related to functionality and adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाएं
    -0.58
    providedIn
    -0.51
    getActiveSheet
    -0.50
    المشاركات
    -0.48
    UpInside
    -0.48
    pyx
    -0.47
    .*")]
    -0.46
    UrlResolution
    -0.46
    arabe
    -0.45
    rinology
    -0.44
    POSITIVE LOGITS
     itself
    0.85
     Itself
    0.74
    itself
    0.73
     covers
    0.60
    covers
    0.58
     zufolge
    0.58
    gives
    0.57
     گوید
    0.57
    andaag
    0.56
     gives
    0.55
    Activations Density 0.842%

    No Known Activations