© 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. 3996
    Prev
    Next
    INDEX
    Explanations

    references to personalized treatment and tailored plans

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

    detailed language about customized professional services like business consulting, therapy, or accounting.

    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
    انيف
    -0.45
     politicians
    -0.44
     فريبيس
    -0.44
    StoryboardSegue
    -0.43
     fancied
    -0.40
     fausse
    -0.40
     lunes
    -0.38
     claims
    -0.38
    ]=="
    -0.38
    *}[
    -0.37
    POSITIVE LOGITS
    🇶
    0.52
    oneofs
    0.48
    исленность
    0.48
     nakalista
    0.43
     informée
    0.43
     förslag
    0.41
    ModelSerializer
    0.41
     rozwiąz
    0.40
    lebnis
    0.40
     säkert
    0.40
    Activations Density 0.093%

    No Known Activations