© 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-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12683
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions associated with creating, listing, or deleting products and tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.66
     CreateTagHelper
    -0.65
    sprodu
    -0.65
    homonymie
    -0.63
    typeorm
    -0.62
    aryen
    -0.60
    ortic
    -0.59
     unknownFields
    -0.58
     siyang
    -0.58
     söyledi
    -0.56
    POSITIVE LOGITS
    able
    0.65
    ing
    0.62
     Solve
    0.61
    apin
    0.55
     Minimize
    0.53
     Kazan
    0.53
     dedicate
    0.53
    InputBorder
    0.52
     Engage
    0.51
     Marry
    0.51
    Activations Density 0.657%

    No Known Activations