© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 9047
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software assemblies and their attributes

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

    Code related to assembly or .NET

    np_acts-logits-general · gemini-2.0-flash

    assembly attributes and .NET assemblies

    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
    ciatore
    -0.63
    enumi
    -0.61
    CWE
    -0.56
     susp
    -0.54
    UPI
    -0.54
     따
    -0.54
     savoury
    -0.53
     proph
    -0.53
    cussed
    -0.53
     spoils
    -0.52
    POSITIVE LOGITS
     Assembly
    1.29
     assembly
    1.24
    assembly
    1.22
    Assembly
    1.13
     ASSEMBLY
    1.09
     AssemblyVersion
    0.93
     assemblies
    0.84
     AssemblyTitle
    0.83
     Assemblies
    0.78
    assemb
    0.73
    Activations Density 0.146%

    No Known Activations