© 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. 4589
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" used in various forms and tenses

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

    the past tense verb "was" appearing at the beginning of sentences or clauses.

    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
     ujednoznacz
    -0.65
    rungsseite
    -0.63
     actualidad
    -0.61
     Currently
    -0.59
    ChildScrollView
    -0.59
    Currently
    -0.55
     ſche
    -0.52
     pleaſure
    -0.52
    NameInMap
    -0.52
     houſe
    -0.51
    POSITIVE LOGITS
     originally
    0.91
     previously
    0.71
     ursprünglich
    0.68
     able
    0.65
     supposed
    0.64
     originalmente
    0.62
     never
    0.61
    originally
    0.61
     initially
    0.60
     formerly
    0.58
    Activations Density 0.555%

    No Known Activations