© 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. 3454
    Prev
    Next
    INDEX
    Explanations

    questions about the possibility or condition of various subjects

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

    a conditional: "if" or "whether"

    np_acts-logits-general · gemini-2.0-flash

    whether or if

    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
     autorytatywna
    -0.89
    دانشنامهٔ
    -0.85
    তথ্যসূত্র
    -0.67
     صوتيه
    -0.64
    findpost
    -0.62
    ScopeManager
    -0.60
    featureID
    -0.59
    basicConfig
    -0.58
    GOTREF
    -0.57
     CURIAM
    -0.57
    POSITIVE LOGITS
     siquiera
    0.35
     there
    0.35
     or
    0.33
    Whether
    0.32
     acaso
    0.30
     jestli
    0.30
     Whether
    0.29
     ever
    0.29
     anyone
    0.29
     anybody
    0.28
    Activations Density 0.303%

    No Known Activations