© 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. 10709
    Prev
    Next
    INDEX
    Explanations

    terms related to "cro" or "Gro" followed by a relevant noun or concept

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

    starting with "cro" or "gro"

    np_acts-logits-general · gemini-2.0-flash

    cro and gro words

    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
     kasarigan
    -0.95
    setVerticalGroup
    -0.78
     ModelExpression
    -0.75
    RegistryLite
    -0.71
    帖最后由
    -0.71
     AssemblyCulture
    -0.68
    MeasureSpec
    -0.66
     HttpNotFound
    -0.64
    hyrchwyd
    -0.63
     endblock
    -0.63
    POSITIVE LOGITS
    ClientSize
    0.45
    MENT
    0.45
    hdysval
    0.44
    ment
    0.43
     kro
    0.43
    ostock
    0.42
    oto
    0.41
    dro
    0.41
     Quite
    0.41
    beforeEach
    0.39
    Activations Density 0.143%

    No Known Activations