© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 1703
    Prev
    Next
    INDEX
    Explanations

    references to celebrities and their events or attributes

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

    followed by capitalization

    np_acts-logits-general · gemini-2.0-flash

    name followed by specific punctuation/word

    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
     dergleichen
    -0.54
     sebagainya
    -0.53
     natomiast
    -0.51
     correspondiente
    -0.47
     denominado
    -0.47
     entspre
    -0.47
     pertinentes
    -0.47
    horabuena
    -0.46
     entsprechenden
    -0.46
     entsprechende
    -0.46
    POSITIVE LOGITS
     Theſe
    0.60
     terrifying
    0.48
     secretly
    0.47
     coronavirus
    0.47
     Anſ
    0.46
     whoſe
    0.46
     theſe
    0.45
     secret
    0.45
     ‘
    0.44
     Jefus
    0.44
    Activations Density 0.168%

    No Known Activations