© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9426
    Prev
    Next
    INDEX
    Explanations

    references to police activities and criminal events involving chases and arrests

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

    Police chases or legal warrants

    np_acts-logits-general · gemini-2.0-flash

    chase and speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.48
     Autorizaciones
    -0.46
     vícti
    -0.44
     Pues
    -0.44
     poème
    -0.42
     colar
    -0.40
     víctima
    -0.39
     víctimas
    -0.39
     tén
    -0.38
    Spenden
    -0.38
    POSITIVE LOGITS
    WebElementEntity
    0.51
     chase
    0.45
     disambiguazione
    0.43
     ExecuteAsync
    0.42
    Diweddarwch
    0.42
     chasing
    0.41
    SupportActionBar
    0.40
    AddTagHelper
    0.39
     &___
    0.38
     chased
    0.38
    Activations Density 0.246%

    No Known Activations