© 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. 12420
    Prev
    Next
    INDEX
    Explanations

    references to reasons and justifications for decisions or actions

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

    "reason" or "reasons"

    np_acts-logits-general · gemini-2.0-flash

    reasons for rejection

    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
     يتيمه
    -0.77
     AssemblyCulture
    -0.63
    adaptiveStyles
    -0.55
     المعيارى
    -0.54
     AssemblyCompany
    -0.54
     NavController
    -0.54
    autorest
    -0.54
    ografija
    -0.54
    secta
    -0.53
    gonic
    -0.53
    POSITIVE LOGITS
     why
    1.19
     behind
    0.86
    why
    0.80
    ableness
    0.71
    ings
    0.70
    behind
    0.69
    ably
    0.66
     waarom
    0.65
     mengapa
    0.63
     warum
    0.63
    Activations Density 0.165%

    No Known Activations