© 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
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7674
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and libraries, particularly related to LINQ and generic collections in .NET

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

    Mathematical and programming terms

    np_acts-logits-general · gemini-2.0-flash

    limits and beginners in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.35
    UnsafeEnabled
    -0.31
     class
    -0.30
    <strong>
    -0.29
     Erhaltung
    -0.29
    </tr>
    -0.29
    nestjs
    -0.28
    abuhan
    -0.28
     dė
    -0.27
     is
    -0.27
    POSITIVE LOGITS
    Linq
    1.66
     EconPapers
    0.77
    stdc
    0.76
    niſſe
    0.73
    Autoritní
    0.73
    ſſung
    0.72
    GEBURTSDATUM
    0.71
     erſt
    0.71
    [@BOS@]
    0.69
    <unused51>
    0.69
    Activations Density 0.023%

    No Known Activations