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. 2-GEMMASCOPE-RES-16K
    6. 15039
    Prev
    Next
    INDEX
    Explanations

    references to formal recognition or awards given to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.74
    
    -0.72
     ModelExpression
    -0.66
    IntoConstraints
    -0.64
    Cyfeiriadau
    -0.60
     IBOutlet
    -0.59
    RectangleBorder
    -0.55
     sẻ
    -0.53
    IBAction
    -0.52
    ORMAL
    -0.52
    POSITIVE LOGITS
     Daß
    0.74
     idéia
    0.70
     confiable
    0.69
     feroit
    0.68
    NUMX
    0.68
     auroit
    0.67
     Neighbor
    0.65
     XNUMX
    0.64
    neighbor
    0.63
    programs
    0.63
    Activations Density 0.559%

    No Known Activations