© 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. 14255
    Prev
    Next
    INDEX
    Explanations

    terms related to sigmoid functions or curves in mathematical contexts

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

    starting with "Sig" or "Vig"

    np_acts-logits-general · gemini-2.0-flash

    sigmoidal / vigorous

    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
     оригіналу
    -0.98
     متعلقه
    -0.85
    DebuggerNonUser
    -0.78
     resourceCulture
    -0.76
     SPDX
    -0.76
    EndInit
    -0.72
    GEBURTSDATUM
    -0.71
    adpleegd
    -0.69
    writeFieldEnd
    -0.68
    Rhestr
    -0.68
    POSITIVE LOGITS
    neurial
    0.53
    jalá
    0.52
    bij
    0.50
    Tig
    0.50
    Jig
    0.49
    Eup
    0.49
     Jig
    0.48
     RIG
    0.48
     Tig
    0.47
     rigs
    0.46
    Activations Density 0.185%

    No Known Activations