© 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 EvalsExportsinterp-engineNEWAPI 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. 3320
    Prev
    Next
    INDEX
    Explanations

    phrases describing geographical or metaphorical boundaries and divisions

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

    the phrase "side of the" (indicating opposing perspectives, boundaries, or dichotomies).

    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
     outsiders
    -0.39
     surrounding
    -0.36
     near
    -0.35
     surrounds
    -0.35
     surround
    -0.34
     surroundings
    -0.34
    BindingSource
    -0.34
     outside
    -0.34
    formik
    -0.33
    周边
    -0.33
    POSITIVE LOGITS
     crossing
    0.96
    Crossing
    0.87
     crossed
    0.86
    crossing
    0.86
    across
    0.84
    Across
    0.82
     Across
    0.81
     Crossing
    0.79
    出版年
    0.78
     bridge
    0.77
    Activations Density 0.157%

    No Known Activations