© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 1913
    Prev
    Next
    INDEX
    Explanations

    references to mathematical concepts and problems related to group theory and complexity

    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
    Personendaten
    -0.69
    parsedMessage
    -0.69
    usermodel
    -0.66
    endpush
    -0.58
    offsetof
    -0.56
     Platform
    -0.56
    }`).
    -0.55
    setVerticalGroup
    -0.55
    findpost
    -0.55
     ModelExpression
    -0.53
    POSITIVE LOGITS
    ]=>
    0.52
    /*
    0.50
     Problem
    0.49
    вест
    0.48
     teore
    0.47
    AuthToken
    0.46
     problem
    0.46
     Catan
    0.46
    iern
    0.45
    GetEnumerator
    0.45
    Activations Density 3.964%

    No Known Activations