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. 25-GEMMASCOPE-RES-16K
    6. 10324
    Prev
    Next
    INDEX
    Explanations

    specific prepositions and related terms in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.68
     ModelExpression
    -0.58
    piac
    -0.55
     Huguen
    -0.54
    raszamy
    -0.50
     Triassic
    -0.50
    ighton
    -0.49
    NGC
    -0.48
    AccessorTable
    -0.47
     Manuela
    -0.47
    POSITIVE LOGITS
    ]();
    0.62
     UserId
    0.46
    /**
    0.46
     miserably
    0.45
    frontmatter
    0.44
     Roses
    0.43
     Adkins
    0.43
     */}
    0.43
     typename
    0.42
     exemple
    0.42
    Activations Density 0.024%

    No Known Activations