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. 10237
    Prev
    Next
    INDEX
    Explanations

    instances of temporal references and transitions in situations

    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
    RectangleBorder
    -0.90
    IsContent
    -0.79
     myſelf
    -0.75
    JspWriter
    -0.71
     Efq
    -0.69
     <",
    -0.69
    DeleteBehavior
    -0.68
     >=",
    -0.68
    InvalidProtocol
    -0.68
    SpringBoot
    -0.67
    POSITIVE LOGITS
    ...
    0.51
     
    0.50
    <eos>
    0.42
    twas
    0.42
    itinéraire
    0.42
     renegoti
    0.42
    cwd
    0.40
     be
    0.40
     by
    0.40
     previously
    0.40
    Activations Density 0.262%

    No Known Activations