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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 3419
    Prev
    Next
    INDEX
    Explanations

    references to equations, figures, and other formal definitions within mathematical discussions

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

    Refers to equations or references

    np_acts-logits-general · gemini-2.0-flash

    equation citation with number

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.65
     createSprite
    -0.59
    WindowConstants
    -0.52
    StoryboardSegue
    -0.51
    newBuilder
    -0.51
    complexContent
    -0.51
    contentLoaded
    -0.50
     tearDown
    -0.50
    marshaller
    -0.49
    getLogger
    -0.49
    POSITIVE LOGITS
     Theſe
    0.72
     Efq
    0.69
     Monfieur
    0.68
     समीक्षाओं
    0.60
    Schicken
    0.59
     Jefus
    0.59
     Chriftian
    0.58
     eût
    0.58
     itſelf
    0.57
     Eſ
    0.57
    Activations Density 0.601%

    No Known Activations