© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5114
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and matches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    opponents or rivals

    np_acts-logits-general · gemini-2.0-flash

    opponents and rivals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.47
     Actividades
    -0.47
     HasFactory
    -0.47
     GenerationType
    -0.46
    __*/
    -0.45
    蚪
    -0.45
    randomUUID
    -0.45
     productivity
    -0.43
    protoc
    -0.43
    ViewChild
    -0.42
    POSITIVE LOGITS
     opponents
    0.71
     opponent
    0.69
     rivales
    0.58
     adversary
    0.56
     rivals
    0.56
     adversaries
    0.56
     сопер
    0.54
    opponent
    0.53
     foes
    0.53
     challeng
    0.51
    Activations Density 0.119%

    No Known Activations