© 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. 22-GEMMASCOPE-RES-16K
    11. 13246
    Prev
    Next
    INDEX
    Explanations

    terms indicating large quantities or significant impact

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

    Following "big" or similar adjectives

    np_acts-logits-general · gemini-2.0-flash

    big and significant things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     very
    -0.76
    very
    -0.67
     muito
    -0.66
     guère
    -0.60
     extremely
    -0.60
     zeer
    -0.57
     매우
    -0.56
    非常に
    -0.56
     entirely
    -0.55
    ReusableCell
    -0.54
    POSITIVE LOGITS
     للمعارف
    0.91
     deal
    0.85
     bummer
    0.78
     shock
    0.73
     difference
    0.72
     disappointment
    0.70
    ConstraintMaker
    0.69
     mouthful
    0.69
     contrast
    0.69
     pleaſure
    0.69
    Activations Density 0.119%

    No Known Activations