© 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. 31-GEMMASCOPE-RES-16K
    11. 9922
    Prev
    Next
    INDEX
    Explanations

    programming or coding-related instructions and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words describing past actions or completed states (past participles and auxiliary verbs indicating completion).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oa̍t
    -0.50
    цездатний
    -0.50
    IndentedString
    -0.49
    хьтан
    -0.41
     ivelany
    -0.41
     Biôgrafia
    -0.40
    Referanser
    -0.40
     للمعارف
    -0.39
    érieures
    -0.39
    MessageOf
    -0.39
    POSITIVE LOGITS
     given
    2.39
    given
    2.14
     provided
    2.11
    Given
    1.89
     Provided
    1.87
    provided
    1.87
     Given
    1.86
     supplied
    1.82
    Provided
    1.79
     GIVEN
    1.78
    Activations Density 0.764%

    No Known Activations