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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 24-GEMMASCOPE-RES-16K
    6. 13963
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to web application versions and errors

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

    Code snippets with "System.Web" elements

    np_acts-logits-general · gemini-2.0-flash

    legal citations starting with Wy

    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
     noDo
    -0.65
    yntaxException
    -0.60
    endforeach
    -0.57
    SizeF
    -0.56
    endphp
    -0.56
    ledem
    -0.54
    erdings
    -0.52
    felves
    -0.51
    vician
    -0.51
    addElement
    -0.50
    POSITIVE LOGITS
    bind
    0.77
     وتسجيلات
    0.55
     arşivlendi
    0.50
    ziała
    0.49
     otoño
    0.49
    urized
    0.48
    AnchorStyles
    0.47
    saraba
    0.46
    client
    0.46
     sguardo
    0.46
    Activations Density 0.167%

    No Known Activations