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. 1-GEMMASCOPE-RES-16K
    6. 13824
    Prev
    Next
    INDEX
    Explanations

    elements and tags used in XML or HTML-like syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.54
    ↵
    -0.51
     (
    -0.49
     per
    -0.46
     in
    -0.46
     “
    -0.46
    ur
    -0.45
     der
    -0.43
     
    -0.43
     and
    -0.42
    POSITIVE LOGITS
    GraphicsUnit
    1.34
    StoryboardSegue
    1.29
    ImageContext
    1.25
    Portale
    1.25
     дописавши
    1.25
    ArgsConstructor
    1.23
     betweenstory
    1.21
    InjectAttribute
    1.19
     onAnimation
    1.19
    awtextra
    1.17
    Activations Density 0.323%

    No Known Activations