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. 11-GEMMASCOPE-RES-16K
    6. 5181
    Prev
    Next
    INDEX
    Explanations

    references to balls in various contexts related to games and play

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hű
    -0.42
     jadx
    -0.40
     extérieures
    -0.39
     σύ
    -0.38
     חיצוני
    -0.37
    rentice
    -0.36
    DebuggerNonUser
    -0.36
     memper
    -0.36
    */;
    -0.35
     sorgen
    -0.35
    POSITIVE LOGITS
     ball
    1.98
     Ball
    1.81
    Ball
    1.77
     BALL
    1.73
     balls
    1.63
    ball
    1.63
     Balls
    1.55
    BALL
    1.52
    Balls
    1.48
    balls
    1.34
    Activations Density 0.076%

    No Known Activations