© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2579
    Prev
    Next
    INDEX
    Explanations

    attributes and versioning information related to software assemblies in a programming context

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

    C# assembly and .NET framework

    np_acts-logits-general · gemini-2.0-flash

    assembly reference

    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
    enumi
    -0.63
    vensko
    -0.49
     Purcell
    -0.46
    OPERATOR
    -0.45
     endwhile
    -0.44
    jago
    -0.43
     enfant
    -0.43
     savoury
    -0.43
     susp
    -0.43
     clinicians
    -0.43
    POSITIVE LOGITS
    assembly
    1.16
     ComVisible
    1.16
     Assembly
    1.14
     assembly
    1.12
    Assembly
    1.08
     AssemblyCulture
    1.07
     ASSEMBLY
    0.93
     typelib
    0.92
     AssemblyVersion
    0.89
     AssemblyTitle
    0.88
    Activations Density 0.077%

    No Known Activations