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. 9983
    Prev
    Next
    INDEX
    Explanations

    connections between clauses or phrases

    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
    ^(@)
    -1.18
     Efq
    -1.18
     Monfieur
    -1.11
     мәкал
    -1.03
     Majefty
    -1.03
    NUMX
    -1.01
     Theſe
    -1.00
    ResumeLayout
    -0.97
     GenerationType
    -0.97
     Reſ
    -0.94
    POSITIVE LOGITS
     thereby
    0.67
    ↵↵
    0.56
    .
    0.52
     thus
    0.51
    </b>
    0.51
     therefore
    0.50
     hence
    0.49
     consequently
    0.48
     also
    0.48
     ainsi
    0.47
    Activations Density 0.723%

    No Known Activations