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. 17-GEMMASCOPE-RES-16K
    6. 7247
    Prev
    Next
    INDEX
    Explanations

    names and roles of players in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -1.08
     Majefty
    -1.01
     Paglinawan
    -0.95
     raiſ
    -0.91
    __":
    
    -0.91
     Houſe
    -0.88
     itſelf
    -0.85
    évaluateur
    -0.85
    AxisAlignment
    -0.83
    Tembelea
    -0.83
    POSITIVE LOGITS
     played
    0.57
     play
    0.56
     scored
    0.56
     inscrit
    0.53
     mencetak
    0.51
     plays
    0.50
     admiti
    0.48
     players
    0.47
     pemain
    0.47
     jugadores
    0.45
    Activations Density 0.168%

    No Known Activations