© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 13569
    Prev
    Next
    INDEX
    Explanations

    monetary values and percentages related to pricing and charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.55
    ThemeOverlay
    -0.49
    RegistryLite
    -0.49
    HasKey
    -0.48
    رشف
    -0.46
    Hentet
    -0.45
    awtextra
    -0.45
    kadang
    -0.45
    gonic
    -0.44
    :+:
    -0.44
    POSITIVE LOGITS
    excess
    0.69
     excess
    0.69
     excesso
    0.67
     exceeding
    0.67
    FTFY
    0.59
    Excess
    0.59
     Excess
    0.59
     exceed
    0.58
     jusqu
    0.58
     exceso
    0.56
    Activations Density 0.347%

    No Known Activations