© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4245
    Prev
    Next
    INDEX
    Explanations

    elements of Java programming syntax and structure

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

    Code snippets: class, object, public

    np_acts-logits-general · gemini-2.0-flash

    class definition, methods

    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
     Савезне
    -0.32
    曖昧さ回避
    -0.31
     influx
    -0.31
    lysses
    -0.30
     respectively
    -0.27
    AVY
    -0.26
     offline
    -0.26
    offline
    -0.26
     stessi
    -0.24
     eins
    -0.24
    POSITIVE LOGITS
    ########.
    0.87
     kaynağından
    0.70
    GraphicsUnit
    0.69
    
    0.68
     Numerade
    0.66
     للمعارف
    0.65
    transQ
    0.64
    disposing
    0.64
    GIVEREF
    0.64
    majánló
    0.62
    Activations Density 0.208%

    No Known Activations