© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 5414
    Prev
    Next
    INDEX
    Explanations

    references to people and their roles or characteristics

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

    followed by prepositions or relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    specific ones or subjects

    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
     kaart
    -0.33
    nościo
    -0.33
     tercero
    -0.33
    けっこう
    -0.33
    adding
    -0.33
    เต็ม
    -0.33
    remainder
    -0.32
     remplissage
    -0.32
     plegable
    -0.32
     theirs
    -0.32
    POSITIVE LOGITS
     Administrativna
    0.77
    ISupport
    0.67
    ThroughAttribute
    0.66
    ReusableCell
    0.65
     kasarigan
    0.65
    MLLoader
    0.62
    fjspx
    0.60
    TestingModule
    0.59
    rungsseite
    0.58
    SpringRunner
    0.57
    Activations Density 1.752%

    No Known Activations