© 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. 7-GEMMASCOPE-RES-16K
    11. 6586
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting in structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tigkeits
    -0.60
    ริง
    -0.60
     Ils
    -0.59
    ieds
    -0.58
     Lindley
    -0.57
    AutoresizingMask
    -0.57
     getIndex
    -0.56
    ExtendWith
    -0.56
    ibouti
    -0.56
    getSystemService
    -0.55
    POSITIVE LOGITS
     تضيفلها
    0.85
     bArr
    0.72
    aspectj
    0.67
    ivable
    0.64
     gră
    0.64
    tableFuture
    0.63
    haway
    0.63
     onAnimation
    0.63
    readAs
    0.61
     שוליים
    0.61
    Activations Density 0.300%

    No Known Activations