© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15934
    Prev
    Next
    INDEX
    Explanations

    references to historical context and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Faulkner
    -0.36
     personalize
    -0.35
     préfé
    -0.34
    hail
    -0.34
     casero
    -0.34
    yaml
    -0.33
    edicated
    -0.33
     samh
    -0.32
     chrétiens
    -0.32
     Monza
    -0.32
    POSITIVE LOGITS
     overseas
    0.88
     Overseas
    0.75
     expatri
    0.74
     expat
    0.70
    海外
    0.69
     exportation
    0.69
     exported
    0.66
     international
    0.66
     shipped
    0.66
    Overseas
    0.64
    Activations Density 0.950%

    No Known Activations