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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 8590
    Prev
    Next
    INDEX
    Explanations

    subcategories or references to sub-elements in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ✨:
    -1.04
     kaynağından
    -0.93
     ModelExpression
    -0.91
     ?>>
    -0.91
    ].)
    -0.89
    rrggbb
    -0.88
     ?>">
    -0.88
     Floren
    -0.87
    parseColor
    -0.87
    %)$
    -0.87
    POSITIVE LOGITS
     sub
    1.99
     Sub
    1.80
     SUB
    1.80
    SUB
    1.79
    sub
    1.65
    Sub
    1.65
     getSub
    1.53
     subs
    1.43
    getSub
    1.35
    サブ
    1.27
    Activations Density 0.136%

    No Known Activations