© 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. 33-GEMMASCOPE-RES-16K
    11. 11427
    Prev
    Next
    INDEX
    Explanations

    statistical values and comparisons related to medical or experimental data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.50
    AddTagHelper
    -0.47
     '\\;'
    -0.45
    ftagPool
    -0.42
    addLast
    -0.34
    ariConfig
    -0.34
    antası
    -0.32
    AnchorStyles
    -0.32
    OCCURRED
    -0.31
    IsMutable
    -0.30
    POSITIVE LOGITS
     ≤
    1.45
     less
    1.45
     exceeding
    1.44
     ≥
    1.44
     <=
    1.38
    小于
    1.34
     $>
    1.33
     >
    1.32
     >=
    1.30
    LessThan
    1.28
    Activations Density 2.736%

    No Known Activations