© 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. 7800
    Prev
    Next
    INDEX
    Explanations

    references to configurations and settings in software applications

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

    Tokens followed by "settings" or "Settings"

    np_acts-logits-general · gemini-2.0-flash

    settings and advanced options

    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
     مرئيه
    -0.72
    KommentareTeilen
    -0.68
    invokeLater
    -0.66
    contentLoaded
    -0.64
    CWE
    -0.55
     OMITBAD
    -0.55
    Aholisi
    -0.55
    AddTagHelper
    -0.53
    äfts
    -0.53
    isContained
    -0.53
    POSITIVE LOGITS
     settings
    2.58
     Settings
    2.17
    settings
    2.09
     setting
    1.96
    Settings
    1.94
     SETTINGS
    1.82
     Setting
    1.78
    setting
    1.67
    Setting
    1.63
     SETTING
    1.58
    Activations Density 0.529%

    No Known Activations