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. 25-GEMMASCOPE-RES-16K
    6. 12584
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "in" and its context within different phrases, emphasizing situations or conditions

    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
    Vidite
    -0.77
     مشارکت‌کنندگان
    -0.65
     للمعارف
    -0.60
    habad
    -0.59
    GraphicsUnit
    -0.59
    initComponents
    -0.56
    README
    -0.55
    windowFixed
    -0.54
    seamnă
    -0.54
    حياته
    -0.54
    POSITIVE LOGITS
     touch
    0.88
     charge
    0.86
     trouble
    0.74
     possession
    0.73
     control
    0.70
     receipt
    0.69
     danger
    0.68
     contact
    0.68
     need
    0.68
     love
    0.67
    Activations Density 0.289%

    No Known Activations