© 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. 31-GEMMASCOPE-RES-16K
    11. 308
    Prev
    Next
    INDEX
    Explanations

    questions that begin with "What."

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

    the beginning of questions, particularly those starting with "What".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.76
    Personendaten
    -0.71
    AndEndTag
    -0.65
    posedge
    -0.60
     disambiguazione
    -0.59
     ModelExpression
    -0.56
    webElementXpaths
    -0.54
    __":
    -0.54
    AddTagHelper
    -0.54
    istoitu
    -0.54
    POSITIVE LOGITS
     kind
    0.71
     are
    0.59
     about
    0.56
     kinds
    0.56
     happens
    0.54
     happened
    0.52
     type
    0.50
    kind
    0.50
     is
    0.49
     sort
    0.48
    Activations Density 0.125%

    No Known Activations