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. 23-GEMMASCOPE-RES-16K
    6. 12190
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific experiments involving protein and gene research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.56
    ########.
    -0.56
    esModule
    -0.53
     ujednoznacz
    -0.52
    脚注の使い方
    -0.51
    createClass
    -0.51
     AspNetCore
    -0.47
    XmlAccessType
    -0.47
    prefixer
    -0.47
    argout
    -0.47
    POSITIVE LOGITS
     control
    1.92
    control
    1.69
     Control
    1.68
     controls
    1.61
    Control
    1.53
     CONTROL
    1.50
     Controls
    1.45
    CONTROL
    1.41
     controles
    1.31
    controls
    1.30
    Activations Density 2.283%

    No Known Activations