© 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. 12679
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or state of being in a formal context

    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
    GeoNames
    -0.50
     disparu
    -0.40
    ArrowToggle
    -0.40
    CloseOperation
    -0.39
    TagHelpers
    -0.38
     Krzyż
    -0.37
    RelativeTo
    -0.37
     Ensino
    -0.36
    ızlık
    -0.36
    回事
    -0.35
    POSITIVE LOGITS
     asked
    1.51
     given
    1.42
     encouraged
    1.36
     instructed
    1.35
     invited
    1.30
     told
    1.29
     allowed
    1.28
     urged
    1.22
    given
    1.20
     advised
    1.19
    Activations Density 0.796%

    No Known Activations