© 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. 12720
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of changes over time and the effects of systems or processes

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

    Auxiliary verbs (is, are, was, were, can, would)

    np_acts-logits-general · gemini-2.0-flash

    changed over, can act, would therefore, were able, is equipped

    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
     espé
    -0.32
    trui
    -0.31
     Privacidade
    -0.30
     suel
    -0.29
     zufried
    -0.29
    뀐
    -0.28
     útiles
    -0.27
     beside
    -0.27
     Ahnung
    -0.27
     bolsillos
    -0.27
    POSITIVE LOGITS
    AndEndTag
    0.89
     resourceCulture
    0.68
    enterOuterAlt
    0.63
    oredCriteria
    0.60
    存于互联网档案馆
    0.60
     CreateTagHelper
    0.60
     Signalez
    0.59
    ExtendWith
    0.57
     Administrativna
    0.57
     ujednoznacz
    0.56
    Activations Density 1.338%

    No Known Activations