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. 11920
    Prev
    Next
    INDEX
    Explanations

    iconic representation markers or attributes related to graphical elements

    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
    +#+#
    -1.09
    abestanden
    -1.06
    RenderAtEndOf
    -0.98
    :✨
    -0.97
    })`
    -0.95
    ViewImports
    -0.93
    IsContent
    -0.92
    })));
    -0.91
    WriteBarrier
    -0.91
    ]--;
    -0.88
    POSITIVE LOGITS
     fa
    1.06
     Fa
    0.74
    fa
    0.69
    Fa
    0.68
    FA
    0.52
     ao
    0.52
    en
    0.48
    團
    0.47
     ta
    0.47
    团
    0.47
    Activations Density 0.017%

    No Known Activations