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-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12316
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to incrementing or counting operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     الحره
    -0.68
     EconPapers
    -0.63
     informée
    -0.59
     كومونز
    -0.58
     JAXBElement
    -0.50
    الحياه
    -0.50
     <=",
    -0.50
    いしい
    -0.49
    出版年
    -0.48
    VYMaps
    -0.48
    POSITIVE LOGITS
    ++;
    1.40
    ++;
    
    1.23
    ]++;
    1.16
     ++;
    0.97
    )++;
    0.93
    ++]
    0.91
    --;
    0.88
    ++];
    0.88
    ++
    0.84
    ++
    
    0.79
    Activations Density 0.116%

    No Known Activations