© 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. 12688
    Prev
    Next
    INDEX
    Explanations

    terms and phrases that indicate effectiveness, suitability, and meaningfulness

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

    Follows words indicating adequacy, suitability, or effectiveness

    np_acts-logits-general · gemini-2.0-flash

    acceptable effectiveness and suitability

    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
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    LookAnd
    -0.79
     autorytatywna
    -0.75
     protoimpl
    -0.67
    ⓧ
    -0.65
    enterOuterAlt
    -0.62
    Personendaten
    -0.55
    帖最后由
    -0.55
    tanleria
    -0.54
     CreateTagHelper
    -0.53
     resourceCulture
    -0.53
    POSITIVE LOGITS
    enough
    0.93
     enough
    0.89
     Theſe
    0.78
    mately
    0.77
     outcomes
    0.70
     ENOUGH
    0.69
    neſs
    0.68
    weise
    0.67
     alternatives
    0.67
     ביותר
    0.66
    Activations Density 0.483%

    No Known Activations