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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 5968
    Prev
    Next
    INDEX
    Explanations

    instances of the word "also" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.73
     pinulongan
    -0.71
     ſind
    -0.71
    neapolis
    -0.69
    getActiveSheet
    -0.68
    SequentialGroup
    -0.66
    ſchen
    -0.66
     myſelf
    -0.65
     indígen
    -0.65
     CURIAM
    -0.65
    POSITIVE LOGITS
    also
    0.76
     also
    0.71
    Also
    0.69
     Also
    0.68
     ALSO
    0.59
    ALSO
    0.54
    また
    0.54
    但也
    0.53
    кож
    0.52
     También
    0.51
    Activations Density 0.136%

    No Known Activations