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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5058
    Prev
    Next
    INDEX
    Explanations

    references to X-ray techniques and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -0.82
    makeConstraints
    -0.76
    Vidite
    -0.75
    numerusform
    -0.70
    CompleteListener
    -0.70
     المعيارى
    -0.69
     استنادى
    -0.69
    '])
    
    -0.68
    DatabaseError
    -0.68
    "])
    
    -0.65
    POSITIVE LOGITS
     X
    3.38
    X
    2.84
     Xs
    1.73
    X
    1.65
    Xs
    1.48
     getX
    1.44
     XX
    1.34
    𝑋
    1.34
    getX
    1.30
     Xt
    1.25
    Activations Density 0.189%

    No Known Activations