© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 24-GEMMASCOPE-RES-16K
    11. 111
    Prev
    Next
    INDEX
    Explanations

    terms related to technological or scientific components and their classifications

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

    Follows names of elements, metals, or languages

    np_acts-logits-general · gemini-2.0-flash

    metal and chemical elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.75
     hObject
    -0.63
     purpoſe
    -0.60
     Geſ
    -0.60
    ſelves
    -0.59
     المعيارى
    -0.59
     Anſ
    -0.59
    addCriterion
    -0.58
     pleaſure
    -0.57
    Kaieteur
    -0.57
    POSITIVE LOGITS
    Nationalité
    0.45
     currencies
    0.44
    currencies
    0.43
     name
    0.43
    Name
    0.42
     countries
    0.40
     Names
    0.39
     Countries
    0.38
     Name
    0.38
     names
    0.38
    Activations Density 1.104%

    No Known Activations