© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1290
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word indicating knowledge or awareness in various contexts

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

    references to the concept of knowledge or understanding in a programming context

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

    NSMutableString / can be / moved back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.64
    MLLoader
    -0.51
    });*/
    -0.51
     ComVisible
    -0.48
     ostavi
    -0.48
    StoryboardSegue
    -0.48
    ooker
    -0.48
     ZAP
    -0.47
    Diverse
    -0.46
    \"");
    -0.44
    POSITIVE LOGITS
    bootstrapcdn
    1.05
     تضيفلها
    0.70
    UnsafeEnabled
    0.69
    chlag
    0.60
    SpringRunner
    0.60
    jsdelivr
    0.60
     pinulongan
    0.58
     onOptions
    0.57
    extAlignment
    0.57
    /*
    0.56
    Activations Density 0.009%

    No Known Activations