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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16059
    Prev
    Next
    INDEX
    Explanations

    numeric values and symbols related to data or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    RenderAtEndOf
    -0.61
    Referanser
    -0.51
     мәкал
    -0.50
    GTCX
    -0.49
     Chwiliwch
    -0.49
    twimg
    -0.48
     Administrativna
    -0.47
     vettoriale
    -0.46
    Réalisation
    -0.42
     cầu
    -0.40
    POSITIVE LOGITS
    HomeAsUp
    0.43
    Parcelize
    0.42
    RectangleBorder
    0.41
    LTRB
    0.39
    genossen
    0.38
     VID
    0.37
    FontOfSize
    0.36
    msgSender
    0.36
    ItemID
    0.36
     '\\;'
    0.36
    Activations Density 2.658%

    No Known Activations