© 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. 15-GEMMASCOPE-RES-16K
    11. 1892
    Prev
    Next
    INDEX
    Explanations

    frequently used adverbs and adjectives in various contexts

    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
     urbana
    -0.68
    jenige
    -0.59
     termica
    -0.58
     térmico
    -0.57
    both
    -0.56
     pubblica
    -0.56
     demais
    -0.55
     tritium
    -0.54
     muerto
    -0.54
     financeira
    -0.54
    POSITIVE LOGITS
     Paglinawan
    0.79
    ]='\
    0.77
     '{@
    0.76
    )";
    0.72
    )$-
    0.69
    ratulations
    0.68
    lynol
    0.67
    iterranean
    0.66
     '}
    0.65
     valid
    0.65
    Activations Density 0.351%

    No Known Activations