© 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. 28-GEMMASCOPE-RES-16K
    11. 7450
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to data analysis and statistical methods

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

    followed by prepositions or parentheses

    np_acts-logits-general · gemini-2.0-flash

    grouped or individual items

    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
    Personendaten
    -0.50
     initComponents
    -0.47
    Geplaatst
    -0.47
    лтамалар
    -0.47
    SharedCtor
    -0.46
    providedIn
    -0.46
     مشين
    -0.46
     perfección
    -0.44
    matchCondition
    -0.42
    WithIOException
    -0.42
    POSITIVE LOGITS
     clustered
    0.55
     individually
    0.53
     scattered
    0.52
    dozen
    0.49
     clustering
    0.48
     numbered
    0.47
     grouped
    0.46
     numbering
    0.46
     NSCoder
    0.46
    arangay
    0.46
    Activations Density 1.603%

    No Known Activations