© 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. 28-GEMMASCOPE-RES-16K
    11. 11196
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or change in context

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

    Preceding "but" and indicating contrast

    np_acts-logits-general · gemini-2.0-flash

    but adjective/adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    exitRule
    -0.47
    AndroidJUnit
    -0.44
     sẵn
    -0.40
     consultato
    -0.40
     CENTRAL
    -0.32
     milder
    -0.32
    hender
    -0.31
     Bo
    -0.31
     Moul
    -0.31
     central
    -0.31
    POSITIVE LOGITS
     (<
    0.75
     AssemblyCulture
    0.61
     зато
    0.57
     وتسجيلات
    0.55
     "..\..\..\
    0.54
    PullParser
    0.54
    ConstraintMaker
    0.53
    astify
    0.53
     AssemblyTitle
    0.51
     كومونز
    0.51
    Activations Density 0.809%

    No Known Activations