Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 11631
    Prev
    Next
    INDEX
    Explanations

    sections of code related to configuration and setup in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lassung
    -0.42
     плен
    -0.42
     kursi
    -0.42
     않
    -0.41
     Evanston
    -0.41
     cheval
    -0.40
    की
    -0.40
    GoogleMap
    -0.39
     gefangen
    -0.39
    istung
    -0.38
    POSITIVE LOGITS
    Xna
    0.96
    gdx
    0.86
     חיצוניים
    0.83
     समीक्षाओं
    0.83
    badlogic
    0.80
     sprites
    0.75
     sprite
    0.69
    adaptiveStyles
    0.68
    CompleteListener
    0.66
     Normdatei
    0.65
    Activations Density 0.140%

    No Known Activations