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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11979
    Prev
    Next
    INDEX
    Explanations

    terms related to medical or legal assessments, evaluations, and findings

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

    after "study," "hearing," or numbers

    np_acts-logits-general · gemini-2.0-flash

    credit and respectively

    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-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
    StoryboardSegue
    -0.74
    WillAppear
    -0.63
    IsContent
    -0.63
    Personendaten
    -0.62
    styleType
    -0.62
    
    -0.60
    enderror
    -0.59
    ActionCreators
    -0.59
    sizeCache
    -0.58
    makeConstraints
    -0.58
    POSITIVE LOGITS
     насељу
    0.37
    openqa
    0.35
    ValueGenerated
    0.35
     training
    0.31
     Neu
    0.29
    ParallelGroup
    0.29
     preliminary
    0.27
    Externé
    0.27
     itemprop
    0.27
     PREL
    0.26
    Activations Density 0.586%

    No Known Activations