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. 12802
    Prev
    Next
    INDEX
    Explanations

    terms related to biomedical field trials and in vivo studies

    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
    AddTagHelper
    -0.50
    featureID
    -0.48
    Personensuche
    -0.41
     مرئيه
    -0.39
     inner
    -0.39
    Binary
    -0.38
     propOrder
    -0.37
     curta
    -0.35
    bellar
    -0.35
    Kont
    -0.35
    POSITIVE LOGITS
    bootstrapcdn
    0.70
     onPostExecute
    0.63
     PublicKey
    0.55
     reale
    0.53
    本番
    0.50
     reales
    0.48
    posedge
    0.48
    getReal
    0.47
    orsese
    0.46
     rzeczyw
    0.46
    Activations Density 0.813%

    No Known Activations