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. 7-GEMMASCOPE-RES-16K
    6. 9130
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "additional" or related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    farin
    -0.66
    Климат
    -0.59
     essentiellement
    -0.57
    Ergebnisse
    -0.56
     sao
    -0.56
     Sao
    -0.56
    matitis
    -0.55
     ILogger
    -0.55
    Jen
    -0.54
     меха
    -0.53
    POSITIVE LOGITS
     additional
    1.73
    Additional
    1.70
    additional
    1.70
     Additional
    1.67
    ADDITIONAL
    1.64
     ADDITIONAL
    1.53
     addi
    1.30
    追加
    1.27
     추가
    1.27
     zusätzlichen
    1.22
    Activations Density 0.140%

    No Known Activations