© 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. 1-GEMMASCOPE-RES-16K
    6. 9004
    Prev
    Next
    INDEX
    Explanations

    scientific references and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſte
    -0.89
     ſta
    -0.83
     ſche
    -0.75
     itſelf
    -0.74
    ſelf
    -0.71
     ſol
    -0.70
     ſmall
    -0.70
     ſch
    -0.69
     verſ
    -0.68
     ſont
    -0.68
    POSITIVE LOGITS
     אתם
    0.33
     BoxFit
    0.32
    AssignableFrom
    0.32
    ļas
    0.31
    ERÍA
    0.31
     בו
    0.31
    stateProvider
    0.31
     בנו
    0.31
     זה
    0.30
     היתה
    0.30
    Activations Density 1.683%

    No Known Activations