© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12153
    Prev
    Next
    INDEX
    Explanations

    numerical values and symbols, likely related to scientific or mathematical data

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

    DOI (Digital Object Identifier) numbers in academic citations and references.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    控
    -0.48
    dAtA
    -0.47
     متعلقه
    -0.46
    ագրություններ
    -0.46
    odles
    -0.46
    הערות
    -0.45
     [*]
    -0.45
     חיצוניים
    -0.45
     שוליים
    -0.45
     enthusi
    -0.44
    POSITIVE LOGITS
     ISSN
    0.74
    ISSN
    0.70
    Personensuche
    0.54
     dtype
    0.45
     Roskov
    0.44
    ViewImports
    0.44
    ISBN
    0.44
     defStyle
    0.43
    DebuggerStep
    0.43
     ISBN
    0.43
    Activations Density 0.060%

    No Known Activations