© 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. 19-GEMMASCOPE-RES-16K
    11. 3186
    Prev
    Next
    INDEX
    Explanations

    references to personal and emotional struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.61
    currently
    -0.53
     currently
    -0.53
     Currently
    -0.50
    このまま
    -0.50
    Currently
    -0.50
     Possibly
    -0.49
     now
    -0.49
    "])
    -0.49
    likely
    -0.48
    POSITIVE LOGITS
     sometimes
    0.96
     бывает
    0.95
    Sometimes
    0.87
     tends
    0.87
    sometimes
    0.86
     always
    0.84
     Sometimes
    0.83
    deauna
    0.83
     oftentimes
    0.83
     člověk
    0.82
    Activations Density 0.617%

    No Known Activations