Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3294
    Prev
    Next
    INDEX
    Explanations

    the introduction or structure of a scientific or technical document

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

    Follows punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    tax authorities

    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
     devait
    -0.57
    >");
    
    -0.55
    }}],
    -0.54
     nacionales
    -0.54
    /");
    -0.53
    /');
    -0.52
    DoubleQuotes
    -0.52
     recommandé
    -0.51
    ]){
    
    -0.50
    pantalón
    -0.50
    POSITIVE LOGITS
    Autoritní
    0.94
    EndContext
    0.75
    OGND
    0.70
    IndentedString
    0.67
     CURIAM
    0.64
    ExtendWith
    0.60
     disambiguazione
    0.60
     pageContext
    0.58
    LookAnd
    0.58
     IBOutlet
    0.57
    Activations Density 0.368%

    No Known Activations