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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9257
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical modeling and definitions associated with data analysis

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

    LaTeX and code delimiters

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code punctuation

    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
     autorytatywna
    -0.95
    rungsseite
    -0.90
     Taktlose
    -0.89
    adaptiveStyles
    -0.87
     Administrativna
    -0.84
     للاسماء
    -0.83
     surla
    -0.80
    httphttps
    -0.79
     EconPapers
    -0.78
    UserScript
    -0.77
    POSITIVE LOGITS
     of
    0.40
     the
    0.38
     $
    0.37
    est
    0.36
     $\
    0.36
     real
    0.35
    ins
    0.35
    .
    0.35
    <h1>
    0.34
    der
    0.34
    Activations Density 2.509%

    No Known Activations