© 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. 4805
    Prev
    Next
    INDEX
    Explanations

    references to organizations and events

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

    Word followed by "components", "in", "with", or "for"

    np_acts-logits-general · gemini-2.0-flash

    places and organizations

    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
     Oll
    -0.49
     Rit
    -0.45
    Fir
    -0.42
    Sal
    -0.41
     Jesse
    -0.41
     epig
    -0.40
    GeoNames
    -0.40
    XmlSchema
    -0.40
    RICO
    -0.40
     Fir
    -0.40
    POSITIVE LOGITS
     createSlice
    0.82
    verwijspagina
    0.68
    ConstraintMaker
    0.56
    TypedDataSet
    0.55
     चीज़ों
    0.52
     NgModule
    0.50
    лтамалар
    0.50
    enderror
    0.50
     snippetHide
    0.49
    ніципалі
    0.48
    Activations Density 1.548%

    No Known Activations