© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8746
    Prev
    Next
    INDEX
    Explanations

    references to skepticism or doubt regarding companies, investments, or policies

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

    Follows modal verbs (would, will, was, is, to)

    np_acts-logits-general · gemini-2.0-flash

    any or anything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.60
     BrowserModule
    -0.56
     CommonModule
    -0.54
    elemField
    -0.53
     actionMode
    -0.52
    TestingModule
    -0.48
     ModelRenderer
    -0.47
    complexContent
    -0.44
    internalType
    -0.43
    GHI
    -0.42
    POSITIVE LOGITS
     siquiera
    0.67
     any
    0.60
     anything
    0.59
     quelconque
    0.58
    そんなに
    0.54
     jemals
    0.54
    kolwiek
    0.49
     quelcon
    0.49
    หร
    0.47
     quaisquer
    0.47
    Activations Density 0.897%

    No Known Activations