© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 536
    Prev
    Next
    INDEX
    Explanations

    the word "Also" and its variations, indicating a focus on additional or supplemental information

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

    the word "also" in text.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.66
     pinulongan
    -0.65
    XmlAccessType
    -0.62
    neapolis
    -0.61
    getActiveSheet
    -0.60
     ſind
    -0.59
     CURIAM
    -0.59
    
    -0.57
     indígen
    -0.57
    SequentialGroup
    -0.56
    POSITIVE LOGITS
    also
    0.85
     also
    0.81
    Also
    0.79
     Also
    0.76
     ALSO
    0.65
    кож
    0.64
    また
    0.60
     וגם
    0.60
    ALSO
    0.60
     juga
    0.60
    Activations Density 0.121%

    No Known Activations