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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1111
    Prev
    Next
    INDEX
    Explanations

    specific brand names and technical terms associated with plumbing and engineering

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

    Uncommon or misspelled words

    np_acts-logits-general · gemini-2.0-flash

    specific names and terms

    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
    RenderAtEndOf
    -0.64
    +#+
    -0.61
    期刊论文
    -0.56
    
    -0.56
    //
    -0.56
     initComponents
    -0.53
    arraycopy
    -0.49
    NSIndexPath
    -0.49
    THISDAY
    -0.48
     saites
    -0.48
    POSITIVE LOGITS
    ftagPool
    0.45
     dAtA
    0.45
    IndentedString
    0.40
    ⟬
    0.36
    лтамалар
    0.35
     المعيارى
    0.34
    rboles
    0.34
     avoient
    0.33
     étoient
    0.33
     <=",
    0.32
    Activations Density 0.784%

    No Known Activations