© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 2522
    Prev
    Next
    INDEX
    Explanations

    technical or structured data entries typically found in programming or documentation contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     â
    -0.81
    ReusableCell
    -0.78
     فريبيس
    -0.71
     تانيه
    -0.69
    ]--;
    -0.63
    ,:),
    -0.62
     …
    -0.62
     fl
    -0.61
    PageFactory
    -0.60
    rigation
    -0.60
    POSITIVE LOGITS
    ...
    0.71
    ....
    0.61
    ...@
    0.61
    Життєпис
    0.59
    Sucesor
    0.57
    "...
    0.57
    يكب
    0.57
     gainera
    0.57
    DeleteBehavior
    0.55
    '...
    0.55
    Activations Density 2.522%

    No Known Activations