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. 15210
    Prev
    Next
    INDEX
    Explanations

    specific numerical data or references

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

    Separators in numerical data

    np_acts-logits-general · gemini-2.0-flash

    French words and titles

    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
     AssemblyCulture
    -0.66
    WriteAttribute
    -0.60
    ParallelGroup
    -0.55
     pinulongan
    -0.54
    ⟬
    -0.52
    Datuak
    -0.52
     Wikimedijinoj
    -0.50
     ſind
    -0.50
    Tikang
    -0.49
     CreateTagHelper
    -0.49
    POSITIVE LOGITS
    Another
    0.47
    Title
    0.42
    Empereur
    0.41
    Already
    0.41
    Ground
    0.40
     vœ
    0.40
    <strong>
    0.40
     évêque
    0.40
     étranger
    0.39
     avoient
    0.39
    Activations Density 0.444%

    No Known Activations