© 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. 30-GEMMASCOPE-RES-16K
    11. 12233
    Prev
    Next
    INDEX
    Explanations

    names and personal details related to individuals in a narrative context

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

    Follows a name or pronoun, then "says" or similar verb

    np_acts-logits-general · gemini-2.0-flash

    reporting verbs

    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
    toMatchSnapshot
    -0.42
    ḏ
    -0.38
    UVWXYZ
    -0.38
    HandlerContext
    -0.37
    Personensuche
    -0.37
     calendriers
    -0.36
     arşivlendi
    -0.35
    readlines
    -0.34
     resourceCulture
    -0.34
     zebra
    -0.33
    POSITIVE LOGITS
     said
    2.11
     says
    1.99
    says
    1.69
     mengatakan
    1.62
    said
    1.61
     Says
    1.52
    Says
    1.48
     SAYS
    1.45
     stated
    1.41
     sagt
    1.40
    Activations Density 0.853%

    No Known Activations