© 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. 11406
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "mark" in various contexts

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

    occurrences of the word "Mark" and its variants.

    oai_token-act-pair · gpt-4oTriggered by @christianthto

    "Mark" followed by a name or title

    np_acts-logits-general · gemini-2.0-flash

    mark followed by surname

    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
    Itoa
    -0.64
    estacks
    -0.53
     المعيارى
    -0.52
     muualla
    -0.52
     виправивши
    -0.51
    lső
    -0.51
    cipit
    -0.50
    عامل
    -0.50
    aleigh
    -0.49
    gnon
    -0.49
    POSITIVE LOGITS
     Twain
    0.85
     dépos
    0.81
    manship
    0.78
    PerformLayout
    0.72
     presença
    0.72
     متحده
    0.69
    ########.
    0.68
     jsPsych
    0.67
     esprits
    0.67
     twain
    0.66
    Activations Density 0.154%

    No Known Activations