© 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. 11607
    Prev
    Next
    INDEX
    Explanations

    patterns of similarity and comparison in descriptions

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

    comparative similarity statements using "behaves/functions... the same as" patterns.

    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
     similarly
    -0.66
    Similarly
    -0.60
     Similarly
    -0.51
    similar
    -0.49
    Matching
    -0.46
    保
    -0.46
    Podob
    -0.43
    Similar
    -0.43
     equally
    -0.41
    同样
    -0.40
    POSITIVE LOGITS
     exactly
    0.57
     للاسماء
    0.51
     EXACTLY
    0.50
     behaves
    0.49
     Exactly
    0.49
     behave
    0.47
     فريبيس
    0.46
     behaving
    0.46
    RenderAtEndOf
    0.46
     exact
    0.46
    Activations Density 0.302%

    No Known Activations