© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3632
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize making or creating significant impressions or changes

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

    "a" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    make a difference

    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
     AssemblyProduct
    -0.59
    MENAFN
    -0.55
    MLLoader
    -0.46
    Reflect
    -0.45
    __':
    
    -0.43
    __':
    -0.43
     StatelessWidget
    -0.42
     capacidades
    -0.42
    fört
    -0.42
     gramas
    -0.41
    POSITIVE LOGITS
     impression
    0.82
     statement
    0.80
     mistake
    0.77
    StateToProps
    0.77
     splash
    0.77
     mockery
    0.75
     dent
    0.74
     Angew
    0.73
     contribution
    0.71
    impression
    0.70
    Activations Density 0.103%

    No Known Activations