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. 24-GEMMASCOPE-RES-16K
    6. 16304
    Prev
    Next
    INDEX
    Explanations

    programming constructs and conditional checks in code snippets

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

    Code snippets with special characters

    np_acts-logits-general · gemini-2.0-flash

    automobile trims and code punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ContentLoaded
    -0.60
    windowFixed
    -0.57
     ligiloj
    -0.57
     AssemblyProduct
    -0.55
    bitField
    -0.55
    featureID
    -0.53
    AndroidJUnit
    -0.49
    omitempty
    -0.49
     ứng
    -0.49
    rasil
    -0.48
    POSITIVE LOGITS
    曖昧さ回避
    0.59
     المعيارى
    0.57
    :✨
    0.52
    CloseOperation
    0.51
    ))));
    0.51
     SEDS
    0.50
    FilterChain
    0.48
     Pingback
    0.48
    )))));
    0.48
     tartalomajánló
    0.48
    Activations Density 0.095%

    No Known Activations