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. 10-GEMMASCOPE-RES-16K
    6. 2540
    Prev
    Next
    INDEX
    Explanations

    references to pairs or groupings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ['./
    -0.93
     Holtz
    -0.91
    })));
    -0.89
     للمعارف
    -0.88
    ABASES
    -0.80
    ,:);
    -0.78
    enment
    -0.78
    antism
    -0.77
    latego
    -0.77
    [@"
    -0.77
    POSITIVE LOGITS
     PAIR
    1.62
     Pair
    1.59
     pair
    1.58
     pairs
    1.56
     paire
    1.47
     Pairs
    1.41
    pair
    1.36
    Pair
    1.35
    PAIR
    1.29
    pairs
    1.24
    Activations Density 0.069%

    No Known Activations