© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 1902
    Prev
    Next
    INDEX
    Explanations

    concepts or discussions surrounding ideas and their implications

    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
    ならない
    -0.66
    eraard
    -0.66
    </em>
    -0.66
     Muñoz
    -0.63
    validations
    -0.63
     Cerv
    -0.62
    roff
    -0.61
     disponibilité
    -0.59
    Notable
    -0.59
    غة
    -0.59
    POSITIVE LOGITS
     ideas
    2.27
    Idea
    2.16
     IDEA
    2.14
     Idea
    2.11
     idea
    2.08
     Ideas
    2.00
    ideas
    1.99
    Ideas
    1.98
    idea
    1.93
    IDEA
    1.87
    Activations Density 0.051%

    No Known Activations