© 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. 11172
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating relationships between ideas or conditions

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

    transitional words and conjunctions that connect clauses or ideas.

    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
    Personendaten
    -0.55
     насељу
    -0.49
    wußt
    -0.49
    ///</
    -0.48
    basicConfig
    -0.45
    bootstrapcdn
    -0.43
    fortawesome
    -0.41
    AntiForgeryToken
    -0.41
    PYX
    -0.40
    _-_
    -0.40
    POSITIVE LOGITS
     even
    4.31
    even
    3.67
     даже
    3.47
     nawet
    3.38
    Even
    3.27
     навіть
    3.19
     sogar
    3.17
     Even
    3.13
     EVEN
    3.05
     bahkan
    3.02
    Activations Density 1.707%

    No Known Activations