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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9099
    Prev
    Next
    INDEX
    Explanations

    terms related to API responses and their metadata

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

    Code snippets or programming-related terms

    np_acts-logits-general · gemini-2.0-flash

    confidence and uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    delwed
    -0.53
    ⓧ
    -0.52
     ujednoznacz
    -0.49
    intermediate
    -0.44
    WriteAttribute
    -0.43
    TokenNameDOT
    -0.43
    Ārējās
    -0.42
     philosophers
    -0.42
    Hampton
    -0.42
    TagHelper
    -0.42
    POSITIVE LOGITS
    BindingResult
    0.43
    PreExecute
    0.41
     apporté
    0.35
    رشف
    0.34
    tikzpicture
    0.34
    брь
    0.33
    setWindow
    0.33
    startY
    0.32
     yyq
    0.32
    AccessException
    0.32
    Activations Density 0.776%

    No Known Activations