Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 12610
    Prev
    Next
    INDEX
    Explanations

    mentions of player debuts and significant achievements in sports

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

    "debut" or "first appearance"

    np_acts-logits-general · gemini-2.0-flash

    making a debut

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    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
    -0.38
    iVar
    -0.34
    原始内容存档于
    -0.33
    browserify
    -0.33
     Relation
    -0.33
    Emphasis
    -0.32
    MemoryWarning
    -0.31
     tó
    -0.31
    取り
    -0.31
    //
    -0.30
    POSITIVE LOGITS
     debut
    1.59
     debuts
    1.31
     Debut
    1.27
    debut
    1.19
     debuted
    1.13
    Debut
    1.12
     estreia
    1.03
     débuts
    0.96
     debu
    0.90
     début
    0.89
    Activations Density 0.143%

    No Known Activations