© 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. 20-GEMMASCOPE-RES-16K
    11. 14959
    Prev
    Next
    INDEX
    Explanations

    elements related to events and markings in a structured context

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

    Sentences followed by a conjunction

    np_acts-logits-general · gemini-2.0-flash

    As followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.61
    afficheront
    -0.59
    LabelTagHelper
    -0.58
     الحره
    -0.57
    astify
    -0.55
    astéroïdes
    -0.53
    Rujuakan
    -0.52
     unknownFields
    -0.49
     nakalista
    -0.49
     كومونز
    -0.48
    POSITIVE LOGITS
     ejecutivo
    0.42
     dermed
    0.41
     coupable
    0.40
     nombrado
    0.39
    Remember
    0.39
     sagrado
    0.39
     peligroso
    0.38
    Lire
    0.38
     interesado
    0.37
    Another
    0.37
    Activations Density 1.345%

    No Known Activations