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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 89188
    Prev
    Next
    INDEX
    Explanations

    present or recent actions and occurrences

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

    just now or recently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Biôgrafia
    -0.42
     따라
    -0.42
     forState
    -0.39
    Rosen
    -0.36
     Soria
    -0.36
    eris
    -0.34
    ştir
    -0.34
     amitié
    -0.34
    ansons
    -0.33
     mikina
    -0.33
    POSITIVE LOGITS
    刚
    0.88
    剛
    0.88
     appena
    0.85
     vừa
    0.84
     recién
    0.83
    刚刚
    0.81
    剛剛
    0.76
     just
    0.73
     recém
    0.73
    :✨
    0.70
    Activations Density 0.008%

    No Known Activations