© 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 EvalsExportsAPI 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. 9320
    Prev
    Next
    INDEX
    Explanations

    positive evaluations about food and dining experiences

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

    preceding location/time words

    np_acts-logits-general · gemini-2.0-flash

    local places and subjects

    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
     surla
    -0.44
     Polri
    -0.41
     Velázquez
    -0.40
     Internasional
    -0.40
     Ausland
    -0.39
     Organización
    -0.39
     maailman
    -0.39
     Mundial
    -0.38
     "..\..\..\
    -0.38
     beginnetje
    -0.37
    POSITIVE LOGITS
     locally
    1.37
     local
    1.34
    locally
    1.18
    local
    1.13
     locals
    1.13
     Locally
    1.09
    Local
    1.09
    Locally
    1.08
     LOCAL
    1.05
     Local
    1.03
    Activations Density 0.943%

    No Known Activations