© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 66055
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to technology and app development

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

    hooked and hook variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Попис
    -0.38
     PLWABN
    -0.34
     Fonten
    -0.31
    \{\\
    -0.29
     stately
    -0.29
     Nor
    -0.29
     Polka
    -0.28
     Erd
    -0.28
     •
    -0.27
     Kl
    -0.27
    POSITIVE LOGITS
    Hook
    1.63
     hook
    1.56
     Hook
    1.54
    hook
    1.54
     HOOK
    1.50
     hooks
    1.41
     hooking
    1.34
     Hooks
    1.34
    HOOK
    1.34
     hooked
    1.32
    Activations Density 0.008%

    No Known Activations