Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3461
    Prev
    Next
    INDEX
    Explanations

    verbs related to leadership and transitions of control

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

    "Took" or "takes" followed by a preposition

    np_acts-logits-general · gemini-2.0-flash

    take charge or over

    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
    
    -0.70
    OGND
    -0.67
    WriteTagHelper
    -0.66
     kasarigan
    -0.65
    DataAnnotations
    -0.65
     المعيارى
    -0.65
     INTO
    -0.64
    Into
    -0.63
    aarrggbb
    -0.62
    PerformLayout
    -0.57
    POSITIVE LOGITS
     charge
    0.80
    charge
    0.58
     CHARGE
    0.57
     aim
    0.57
    Took
    0.56
     Takes
    0.56
     Charge
    0.55
     Took
    0.53
    Ủ
    0.52
    Charge
    0.52
    Activations Density 0.085%

    No Known Activations