© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5909
    Prev
    Next
    INDEX
    Explanations

    specific implementation names and terms related to software or database systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Obrador
    -0.70
    TypedDataSet
    -0.56
    tvguidetime
    -0.55
    ActionCreators
    -0.54
    skate
    -0.53
    UserScript
    -0.52
    Skate
    -0.50
    esticular
    -0.50
    wwwwwwww
    -0.50
    therin
    -0.49
    POSITIVE LOGITS
     Group
    0.40
     Kritik
    0.40
     Alliance
    0.40
     незавершена
    0.39
    CONDITION
    0.39
     takk
    0.37
     alianza
    0.37
     Meridian
    0.36
     fusión
    0.36
     Plenty
    0.36
    Activations Density 1.420%

    No Known Activations