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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9544
    Prev
    Next
    INDEX
    Explanations

    instances of the term "shower" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tel
    -0.57
     Contro
    -0.57
    Personensuche
    -0.57
     Main
    -0.53
    Билгалдахарш
    -0.52
     TestBed
    -0.51
    LabelTagHelper
    -0.51
     merce
    -0.50
     vol
    -0.50
    Contro
    -0.49
    POSITIVE LOGITS
     inesperado
    0.66
     unexpected
    0.63
     uncomfortable
    0.60
     civilización
    0.60
     Italij
    0.59
     unwelcome
    0.59
     navideña
    0.59
     bruja
    0.58
     unpleasant
    0.58
     navideño
    0.56
    Activations Density 0.253%

    No Known Activations