© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7312
    Prev
    Next
    INDEX
    Explanations

    references to academic articles or journals

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

    astrophysical journals

    np_acts-logits-general · gemini-2.0-flash

    journal abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueGenerated
    -0.50
     مشين
    -0.47
    WriteTagHelper
    -0.46
    localctx
    -0.46
    তথ্যসূত্র
    -0.46
    indd
    -0.45
     שוליים
    -0.43
     Akismet
    -0.42
     Organics
    -0.41
     estekak
    -0.41
    POSITIVE LOGITS
    ceedings
    0.43
    íncia
    0.41
     Review
    0.39
    bootstrapcdn
    0.39
    rungsseite
    0.38
     kohdetta
    0.38
    bundles
    0.37
    lassified
    0.37
     tartalomajánló
    0.36
    Contributed
    0.36
    Activations Density 0.646%

    No Known Activations