© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15632
    Prev
    Next
    INDEX
    Explanations

    medical conditions or injuries, particularly those that involve physical trauma or ailments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    medical conditions and injury descriptions.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lindungi
    -0.43
    毂
    -0.43
    Biographie
    -0.42
     rękaw
    -0.42
    wnicy
    -0.41
     koszulka
    -0.41
     dostępne
    -0.41
     mikina
    -0.40
     diritti
    -0.40
     vostri
    -0.40
    POSITIVE LOGITS
     AssemblyCompany
    0.41
     protoimpl
    0.39
     LayoutInflater
    0.38
    UnusedPrivate
    0.38
     ErrIntOverflow
    0.36
     HasFactory
    0.36
    URLEncoder
    0.36
    IsContent
    0.36
     Pamph
    0.35
    complexContent
    0.35
    Activations Density 0.245%

    No Known Activations