© 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. 4386
    Prev
    Next
    INDEX
    Explanations

    references to conferences and discussions about them

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

    "conference" or its plurals

    np_acts-logits-general · gemini-2.0-flash

    conference events and discussions

    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
    enumi
    -0.43
     Ayuda
    -0.41
    SizeMode
    -0.41
     вікісторінку
    -0.40
    Mary
    -0.39
    QMetaType
    -0.39
    Methyl
    -0.38
    Vegetable
    -0.37
    Jill
    -0.36
    victim
    -0.36
    POSITIVE LOGITS
     conference
    2.03
     Conference
    2.02
    Conference
    1.91
     conferences
    1.86
     CONFERENCE
    1.84
    conference
    1.79
     Conferences
    1.78
     konfer
    1.59
     Konferenz
    1.49
     Confer
    1.45
    Activations Density 0.085%

    No Known Activations