© 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. 3481
    Prev
    Next
    INDEX
    Explanations

    terms associated with "sm" and its variations, particularly in software and programming contexts

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

    starting with "Sm" or "sm"

    np_acts-logits-general · gemini-2.0-flash

    sm

    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
     ProtoMessage
    -0.77
    Geplaatst
    -0.72
    ItemBackground
    -0.69
    öglichkeiten
    -0.68
    TemporalType
    -0.66
    ElementException
    -0.66
    toEqual
    -0.61
    RoutingModule
    -0.61
    ‍♂️
    -0.60
    tagHelperRunner
    -0.59
    POSITIVE LOGITS
     Sm
    0.91
     sm
    0.88
     SM
    0.88
     SMI
    0.87
    Sm
    0.86
     Smar
    0.84
     Smiley
    0.81
    sonian
    0.79
    SM
    0.77
     smit
    0.72
    Activations Density 0.105%

    No Known Activations