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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 5855
    Prev
    Next
    INDEX
    Explanations

    visibility modifiers and function declarations in code

    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
     initComponents
    -0.97
     myſelf
    -0.95
     समीक्षाओं
    -0.88
     Majefty
    -0.77
    ſelf
    -0.77
     ſeveral
    -0.76
     itſelf
    -0.76
     raiſ
    -0.76
    UAGES
    -0.74
     ſmall
    -0.74
    POSITIVE LOGITS
    templateUrl
    0.59
     Thus
    0.53
    UObject
    0.52
    だからこそ
    0.51
    ագրություններ
    0.50
     couver
    0.50
    Thus
    0.47
     &
    0.47
     Yet
    0.46
    FOUND
    0.46
    Activations Density 0.237%

    No Known Activations