© 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. 7427
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or ambivalence

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

    Text following sentence endings or list items

    np_acts-logits-general · gemini-2.0-flash

    live rolling coverage

    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
     stated
    -0.40
    geslacht
    -0.33
    ywna
    -0.33
    مقال
    -0.31
     Einf
    -0.31
    beruf
    -0.31
    Odkazy
    -0.30
     selected
    -0.30
    似的
    -0.29
     methods
    -0.29
    POSITIVE LOGITS
    MigrationBuilder
    0.84
    Personensuche
    0.66
    ValueStyle
    0.65
    Portail
    0.64
    цездатний
    0.61
    ConstraintMaker
    0.60
     tonight
    0.59
    endphp
    0.59
    Tonight
    0.58
    omock
    0.58
    Activations Density 0.062%

    No Known Activations