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. 9-GEMMASCOPE-RES-16K
    6. 7943
    Prev
    Next
    INDEX
    Explanations

    keywords related to component definitions and lifecycle methods in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     himſelf
    -0.88
     Efq
    -0.87
    RTDA
    -0.86
    RUnlock
    -0.83
     myſelf
    -0.83
     Shakspeare
    -0.82
     Monfieur
    -0.81
     itſelf
    -0.81
     poffe
    -0.79
     Administrativna
    -0.78
    POSITIVE LOGITS
     evt
    0.65
     nahilalakip
    0.63
     Tax
    0.61
    󠁿
    0.58
     hot
    0.57
     getS
    0.57
    entery
    0.56
    ′
    0.56
     Arch
    0.55
     Hot
    0.55
    Activations Density 0.008%

    No Known Activations