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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 91267
    Prev
    Next
    INDEX
    Explanations

    biomarkers and genetic mutations related to cancer and targeted therapies

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

    tyrosine kinase signaling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Geplaatst
    -0.48
    hygiène
    -0.45
     transfieras
    -0.45
    serviceWorker
    -0.45
    GraphicsUnit
    -0.43
    pgterms
    -0.41
     Pig
    -0.41
    endforeach
    -0.41
    +#+
    -0.40
    ituary
    -0.40
    POSITIVE LOGITS
     tyrosine
    0.58
     InputDecoration
    0.49
     EGFR
    0.47
     viewDidLoad
    0.47
    rosine
    0.44
    IntoConstraints
    0.42
     ffilmiau
    0.41
     Eurasia
    0.41
    Personendaten
    0.40
     frau
    0.39
    Activations Density 0.113%

    No Known Activations