© 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. 16382
    Prev
    Next
    INDEX
    Explanations

    names and references to individuals involved in various contexts, particularly those related to expertise or notable actions

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

    Precedes names or abbreviations

    np_acts-logits-general · gemini-2.0-flash

    Scott last name phrases

    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
     allAfrica
    -0.51
     ge
    -0.46
    baga
    -0.45
    mak
    -0.44
     Ge
    -0.44
    펴
    -0.44
    rogens
    -0.43
     CIV
    -0.43
     мәкалә
    -0.43
    æv
    -0.42
    POSITIVE LOGITS
    CppMethod
    0.70
    IntoConstraints
    0.66
    UnsafeEnabled
    0.61
    setVerticalGroup
    0.59
    rungsseite
    0.57
    MLLoader
    0.57
    anmoins
    0.57
    AccessorTable
    0.56
    AnchorStyles
    0.55
    EndProject
    0.55
    Activations Density 0.145%

    No Known Activations