© 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. 5700
    Prev
    Next
    INDEX
    Explanations

    references to people and their relationships in various contexts

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

    Follows a capitalized word or abbreviation

    np_acts-logits-general · gemini-2.0-flash

    really, indeed, actually

    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
     ovviamente
    -0.90
     reportedly
    -0.80
     oczywiście
    -0.78
     natuurlijk
    -0.77
     natürlich
    -0.75
    Obvious
    -0.74
     évidemment
    -0.73
     tentu
    -0.71
     Obviously
    -0.70
     obviamente
    -0.70
    POSITIVE LOGITS
     really
    0.89
     efectivamente
    0.87
     indeed
    0.83
    really
    0.83
     للمعارف
    0.81
     وأن
    0.81
    DockStyle
    0.80
    Really
    0.79
     fakty
    0.78
     actually
    0.78
    Activations Density 0.833%

    No Known Activations