© 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. 30-GEMMASCOPE-RES-16K
    6. 12298
    Prev
    Next
    INDEX
    Explanations

    pronouns and references to social interactions or relationships

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

    "As [pronoun] [verb]" at the start of a sentence

    np_acts-logits-general · gemini-2.0-flash

    "as" followed by subject and action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abstrato
    -0.40
    udayaan
    -0.39
     muuta
    -0.39
     kysy
    -0.35
    autaire
    -0.34
     Wählen
    -0.34
     joten
    -0.34
     použ
    -0.33
     Gleaner
    -0.33
    ⓧ
    -0.33
    POSITIVE LOGITS
    AddTagHelper
    0.80
     prepares
    0.78
     progresses
    0.73
     nears
    0.71
     increasingly
    0.66
     prepare
    0.66
     continues
    0.65
     slowly
    0.64
     struggles
    0.62
     approaches
    0.60
    Activations Density 0.179%

    No Known Activations