© 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. 40-GEMMASCOPE-RES-16K
    11. 1922
    Prev
    Next
    INDEX
    Explanations

    elements related to technical specifications and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.52
    DebuggerNonUser
    -0.49
    AddTagHelper
    -0.48
     متعلقه
    -0.47
    帖最后由
    -0.46
    исленность
    -0.46
    󠁮
    -0.46
     removeFrom
    -0.43
     Chwiliwch
    -0.42
    ///</
    -0.42
    POSITIVE LOGITS
     having
    2.91
    having
    2.56
     Having
    2.42
    Having
    2.42
     HAVING
    2.20
     иметь
    1.87
     avere
    1.84
     memiliki
    1.81
     have
    1.74
     mempunyai
    1.66
    Activations Density 1.164%

    No Known Activations