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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2199
    Prev
    Next
    INDEX
    Explanations

    punctuations and sentence transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.51
    बर
    -0.47
    jenost
    -0.45
    Tembelea
    -0.43
     low
    -0.42
    bet
    -0.42
     Wür
    -0.42
     oprot
    -0.42
    offen
    -0.41
     وسلم
    -0.40
    POSITIVE LOGITS
    
    0.82
     indietro
    0.66
    IGraphics
    0.65
    awaiter
    0.65
     الرياضيه
    0.64
    RectangleBorder
    0.64
     >=",
    0.64
    WEBPACK
    0.63
     Dafür
    0.63
    TargetException
    0.63
    Activations Density 0.901%

    No Known Activations