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. 13-GEMMASCOPE-RES-16K
    6. 4342
    Prev
    Next
    INDEX
    Explanations

    structured data primarily in the form of arrays or programming patterns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Brainz
    -0.83
    Enllaces
    -0.79
    DispatchToProps
    -0.70
    ArgsConstructor
    -0.69
    didSet
    -0.68
    bukkit
    -0.67
    ftagPool
    -0.67
    рення
    -0.66
    JNIEnv
    -0.66
    FXML
    -0.65
    POSITIVE LOGITS
     VIDEOTAPE
    0.47
    яз
    0.47
    止
    0.46
    ul
    0.46
     trânsito
    0.45
    ig
    0.45
    勅
    0.44
    esch
    0.44
    dy
    0.42
    ctis
    0.42
    Activations Density 0.137%

    No Known Activations