© 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. 6959
    Prev
    Next
    INDEX
    Explanations

    negation or qualifiers indicating exclusivity

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

    "Either", "only", "not", or "even"

    np_acts-logits-general · gemini-2.0-flash

    qualifying conditions or exceptions

    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
     jonka
    -0.40
     meilleure
    -0.38
     implique
    -0.38
    żym
    -0.37
     которого
    -0.37
     involucra
    -0.36
     Someone
    -0.36
     alguien
    -0.36
    guien
    -0.36
     Jop
    -0.35
    POSITIVE LOGITS
     nahilalakip
    0.61
     autorytatywna
    0.59
     CreateTagHelper
    0.55
     Exactos
    0.54
     فريبيس
    0.54
    ScopeManager
    0.52
    AutoScaleMode
    0.51
    thâu
    0.50
     Exacts
    0.48
     ***!
    0.48
    Activations Density 0.481%

    No Known Activations