© 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. 8581
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to be" and expressions of certainty or doubt

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

    contractions with "is" or "has" (specifically the "'s" contraction form).

    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
    SourceChecksum
    -0.44
     беше
    -0.35
    ioutil
    -0.27
    بوابة
    -0.27
     Wiktionnaire
    -0.27
    OGND
    -0.26
     oculto
    -0.25
     חיצוניים
    -0.25
    万美元
    -0.25
     Guiana
    -0.24
    POSITIVE LOGITS
     been
    2.03
    been
    1.47
     BEEN
    1.44
     got
    1.41
     Been
    1.38
    Been
    1.35
     gotten
    1.24
     gone
    1.16
     become
    1.07
     undergone
    1.05
    Activations Density 0.363%

    No Known Activations