Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 1667
    Prev
    Next
    INDEX
    Explanations

    C++ syntax elements and namespace usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onBind
    -0.76
    
    -0.75
    ">@
    -0.71
     createSlice
    -0.68
     Roskov
    -0.66
     Référence
    -0.66
    daging
    -0.66
    ">'.$
    -0.64
    ]<<
    -0.63
     chi̍t
    -0.63
    POSITIVE LOGITS
    IActionResult
    0.49
    RRect
    0.48
    FillColor
    0.47
     оригіналу
    0.44
     Вікі
    0.44
     eventdata
    0.43
    crity
    0.42
     BoxDecoration
    0.42
    сибир
    0.42
    смотря
    0.42
    Activations Density 0.036%

    No Known Activations