Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 3914
    Prev
    Next
    INDEX
    Explanations

    elements of dining experiences and interactions in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.55
    =$?
    -0.50
     integrand
    -0.48
    argout
    -0.48
    thenia
    -0.47
    Occurred
    -0.47
    ticale
    -0.47
    Accum
    -0.47
    сшта
    -0.46
    scales
    -0.46
    POSITIVE LOGITS
     seats
    1.31
     spots
    1.27
     spaces
    1.16
     reserved
    1.15
     slots
    1.07
     space
    1.03
    reserved
    1.02
    spots
    1.01
     Reserved
    0.99
     Seats
    0.99
    Activations Density 0.338%

    No Known Activations