© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12589
    Prev
    Next
    INDEX
    Explanations

    structured data representations, especially tables and records

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

    Numbers followed by a colon

    np_acts-logits-general · gemini-2.0-flash

    column separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.57
    )]
    -0.55
     :
    -0.54
     ་་
    -0.53
    ."],
    -0.53
    )))),
    -0.53
     ''),
    -0.52
    :,,
    -0.51
    "},
    -0.51
    DebuggerNonUser
    -0.51
    POSITIVE LOGITS
    ViewFeatures
    0.55
    
    0.44
    География
    0.42
     argint
    0.36
    numerusform
    0.33
     defaultstate
    0.33
    lético
    0.32
     DIFFERENCE
    0.32
     żyw
    0.31
    SizeF
    0.31
    Activations Density 1.473%

    No Known Activations