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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 15729
    Prev
    Next
    INDEX
    Explanations

    words that start with "sn" or contain the substring "sn"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ])):
    -0.65
     ModelExpression
    -0.63
    suya
    -0.60
    umet
    -0.58
    stdbool
    -0.55
    ]>=
    -0.55
    PerformLayout
    -0.54
    큼
    -0.54
    "]));
    -0.53
    richtet
    -0.52
    POSITIVE LOGITS
     Sna
    1.09
     Sn
    1.04
    Snoo
    1.01
     SN
    0.99
    Sna
    0.95
    Sn
    0.94
     sna
    0.91
    sna
    0.89
     sn
    0.88
     SNA
    0.86
    Activations Density 0.091%

    No Known Activations