© 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. 18-GEMMASCOPE-RES-16K
    11. 3456
    Prev
    Next
    INDEX
    Explanations

    words and terms related to Crohn's disease and its associations

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

    Begins with "cro" or "gro"

    np_acts-logits-general · gemini-2.0-flash

    cro and gro prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帖最后由
    -0.70
    NotBlank
    -0.62
     kasarigan
    -0.62
    nsf
    -0.59
    DeleteCommand
    -0.59
    pinephrine
    -0.59
    RegistryLite
    -0.59
    cemia
    -0.57
    FlatAppearance
    -0.56
    othek
    -0.56
    POSITIVE LOGITS
     kro
    0.76
    dro
    0.68
     CRO
    0.67
     Crot
    0.66
     Kro
    0.62
    cro
    0.62
    GRO
    0.61
    Kro
    0.61
    iro
    0.59
     Puro
    0.58
    Activations Density 0.196%

    No Known Activations