© 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. 18-GEMMASCOPE-RES-16K
    11. 3980
    Prev
    Next
    INDEX
    Explanations

    sentences that express gratitude or recognition of contributions

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

    Words/phrases followed by "that" or "the"

    np_acts-logits-general · gemini-2.0-flash

    reporting verbs followed by that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.84
     nakalista
    -0.81
    rrggbb
    -0.75
     صوتيه
    -0.71
    gypti
    -0.69
    XmlAccessType
    -0.67
    findpost
    -0.66
    StoredProcedure
    -0.64
    )_/¯
    -0.64
    例文帳に追加
    -0.62
    POSITIVE LOGITS
    ว่า
    0.75
     bahwa
    0.65
     that
    0.62
     faptul
    0.57
     että
    0.56
     bahawa
    0.51
     ότι
    0.49
     about
    0.47
     rằng
    0.43
     to
    0.43
    Activations Density 0.262%

    No Known Activations