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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 3969
    Prev
    Next
    INDEX
    Explanations

    references to specific assembly attributes in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cellpadding
    -0.68
    featureID
    -0.67
    EndContext
    -0.64
    dersfield
    -0.61
    ArgsConstructor
    -0.61
     civiles
    -0.60
    WithMany
    -0.57
     الحره
    -0.56
    findpost
    -0.56
    ParallelGroup
    -0.55
    POSITIVE LOGITS
    assembly
    2.02
     assembly
    1.47
    Assembly
    1.39
     Assembly
    1.29
     ASSEMBLY
    1.19
     assemblies
    1.04
    sembly
    0.92
     Assemblies
    0.87
     assembler
    0.82
    assembled
    0.81
    Activations Density 0.022%

    No Known Activations