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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1026
    Prev
    Next
    INDEX
    Explanations

    syntactic structures and declarations in programming code

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

    Code, math, or special characters

    np_acts-logits-general · gemini-2.0-flash

    Groups A and C

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    jooq
    -0.60
     Infórmanos
    -0.56
     ASF
    -0.55
     विश्वसनीयता
    -0.55
     '\\;'
    -0.54
    Geplaatst
    -0.52
    awtextra
    -0.52
     RSC
    -0.50
     CSF
    -0.50
     SPS
    -0.49
    POSITIVE LOGITS
     inalámbrico
    0.40
     *)(
    0.35
     financiamiento
    0.34
     intStringLen
    0.34
    complexContent
    0.34
     psicológica
    0.34
    angé
    0.34
    niosek
    0.34
     rodzic
    0.33
     logistique
    0.33
    Activations Density 0.186%

    No Known Activations