© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 15293
    Prev
    Next
    INDEX
    Explanations

    specific vocabulary related to actions and processes, particularly in formal and structured contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.35
    +#+
    -0.34
    genheiten
    -0.32
    ありました
    -0.30
    あります
    -0.30
    JspWriter
    -0.29
    あるので
    -0.28
     Autorisations
    -0.28
     Zwecke
    -0.27
    amitié
    -0.25
    POSITIVE LOGITS
    ing
    2.34
    ING
    2.05
    ings
    1.91
     ing
    1.52
    ingly
    1.51
    ning
    1.49
    िंग
    1.48
    inge
    1.45
    íng
    1.44
    INGS
    1.41
    Activations Density 1.266%

    No Known Activations