© 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. 3979
    Prev
    Next
    INDEX
    Explanations

    statements or phrases that express assumptions or hypotheses

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

    "assume" or "assumed"

    np_acts-logits-general · gemini-2.0-flash

    assume 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
    ye
    -0.52
    p
    -0.49
     téléchargez
    -0.48
    ilo
    -0.47
     venons
    -0.47
     StatelessWidget
    -0.47
    انا
    -0.46
    へ
    -0.46
    子
    -0.46
    charCodeAt
    -0.46
    POSITIVE LOGITS
     Assumptions
    0.94
    Personensuche
    0.93
    PerformLayout
    0.90
     виправивши
    0.90
     assume
    0.88
     assumes
    0.83
    الإنجليزية
    0.82
     Baillargeon
    0.82
    WebElementEntity
    0.78
    assume
    0.78
    Activations Density 0.159%

    No Known Activations