© 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. 4766
    Prev
    Next
    INDEX
    Explanations

    references to JSON formatting and operations

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

    Code or text related to JSON

    np_acts-logits-general · gemini-2.0-flash

    json parsing and stringifying

    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
     bekym
    -0.48
    rawdź
    -0.47
     imageName
    -0.46
     AppColors
    -0.45
    ordnung
    -0.45
     bege
    -0.44
     tensione
    -0.44
    বে
    -0.44
     Trinity
    -0.43
     UIT
    -0.43
    POSITIVE LOGITS
    पया
    0.76
    PointerException
    0.71
    rpc
    0.67
    addGap
    0.63
    ld
    0.60
    expandindo
    0.59
    adə
    0.59
    djangoproject
    0.58
     protoimpl
    0.58
    BeginContext
    0.57
    Activations Density 0.092%

    No Known Activations