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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3593
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their performances

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

    "recent" or "last"

    np_acts-logits-general · gemini-2.0-flash

    recent past actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ayam
    -0.42
     bourbon
    -0.39
    หว่าง
    -0.37
     Proz
    -0.36
    Titan
    -0.36
    Retro
    -0.36
    Geografie
    -0.36
    Hire
    -0.35
    PositiveButton
    -0.35
     Tofu
    -0.35
    POSITIVE LOGITS
     recent
    0.71
    recently
    0.64
    recent
    0.63
     recently
    0.63
     reciente
    0.61
     last
    0.59
     recente
    0.59
     HasFactory
    0.59
     recientes
    0.57
     vorige
    0.56
    Activations Density 0.131%

    No Known Activations