© 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. 15-GEMMASCOPE-RES-16K
    6. 8908
    Prev
    Next
    INDEX
    Explanations

    terms related to data structures and programming concepts

    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
    IonicModule
    -0.72
    windowFixed
    -0.70
    دانشنامهٔ
    -0.69
    rrbracket
    -0.66
    EndContext
    -0.64
    HomeAsUpEnabled
    -0.60
     Meksiku
    -0.60
    "]);
    
    -0.59
    цездатний
    -0.58
    encodeWith
    -0.57
    POSITIVE LOGITS
    RenderAtEndOf
    0.88
    StoryboardSegue
    0.59
     dedicated
    0.59
     called
    0.54
    Referències
    0.50
    HttpFoundation
    0.49
    叫做
    0.47
     sahiptir
    0.47
     daarvoor
    0.46
    feira
    0.46
    Activations Density 0.937%

    No Known Activations