© 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. 12679
    Prev
    Next
    INDEX
    Explanations

    phrases related to gratitude or appreciation

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

    expressions of emphasis or intensification, particularly words like "enough," "not," and "fast" that strengthen or negate statements.

    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
    TestingModule
    -0.44
    AppMethodBeat
    -0.43
    httphttps
    -0.42
     übrigens
    -0.41
     étoit
    -0.39
    UrlResolution
    -0.39
    WriteBarrier
    -0.39
    einander
    -0.39
    XmlIgnore
    -0.39
    Tazama
    -0.38
    POSITIVE LOGITS
     enough
    4.00
    enough
    3.52
     Enough
    3.47
     sufficient
    3.25
    Enough
    3.23
     ENOUGH
    3.11
     Sufficient
    2.91
     suficiente
    2.73
    sufficient
    2.72
     sufficiently
    2.70
    Activations Density 1.684%

    No Known Activations