© 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. 2622
    Prev
    Next
    INDEX
    Explanations

    HTML span tags and their attributes

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

    HTML `span` tag

    np_acts-logits-general · gemini-2.0-flash

    HTML span tags

    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
    gelöst
    -0.35
    __":
    -0.34
     élections
    -0.33
    __':
    -0.33
     erstes
    -0.32
     Harrell
    -0.31
     joueurs
    -0.30
     erste
    -0.30
     limpio
    -0.30
     invitar
    -0.30
    POSITIVE LOGITS
    span
    2.89
     span
    2.39
    Span
    2.25
     Span
    2.20
     SPAN
    2.08
    SPAN
    2.05
    spans
    2.02
     spans
    1.77
     spanned
    1.55
    spanning
    1.48
    Activations Density 0.108%

    No Known Activations