© 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-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 12985
    Prev
    Next
    INDEX
    Explanations

    descriptions and representations of characters in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SOFT
    -0.64
    Soft
    -0.63
     Soft
    -0.61
     softness
    -0.58
     soft
    -0.57
    MemoryWarning
    -0.57
     weich
    -0.55
     insuffisamment
    -0.54
    soft
    -0.54
    SOFT
    -0.53
    POSITIVE LOGITS
     hardcore
    0.79
     gritty
    0.76
     austere
    0.76
     tough
    0.73
    tough
    0.71
     grim
    0.71
     somber
    0.71
     grit
    0.70
    严肃
    0.70
    Tough
    0.70
    Activations Density 0.606%

    No Known Activations