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. 12-GEMMASCOPE-RES-16K
    6. 2730
    Prev
    Next
    INDEX
    Explanations

    hierarchical structures and navigation elements in code or documentation

    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
     ModelExpression
    -0.98
    ✨:
    -0.97
     Floren
    -0.92
     ?>">
    -0.87
     ?>>
    -0.87
     kaynağından
    -0.85
    ).)
    -0.84
     RequestMethod
    -0.84
     }}"></
    -0.84
    ="#">
    -0.83
    POSITIVE LOGITS
     SUB
    1.52
    SUB
    1.49
     sub
    1.48
     Sub
    1.44
    Sub
    1.28
     subs
    1.25
    sub
    1.24
     getSub
    1.23
    getSub
    1.09
    サブ
    0.99
    Activations Density 0.146%

    No Known Activations