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. 8105
    Prev
    Next
    INDEX
    Explanations

    terms related to volleyball and its gameplay

    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
     consultato
    -0.55
    +#+#
    -0.55
    الحياه
    -0.55
     <<<<<<<<<<<<<<
    -0.54
    Hochspringen
    -0.53
    UnitTesting
    -0.52
     برانيه
    -0.52
    mancy
    -0.51
    ViewFeatures
    -0.51
    DOCTYPE
    -0.50
    POSITIVE LOGITS
     serve
    0.98
     libero
    0.93
     setter
    0.92
     serving
    0.89
     kills
    0.88
     volleyball
    0.87
     service
    0.83
     kill
    0.81
    Serving
    0.81
    serving
    0.80
    Activations Density 0.119%

    No Known Activations