© 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. 14412
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or patterns related to specific terms and references in context

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

    the word "the" appearing before nouns or descriptive terms in formal or technical text.

    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
     snippetHide
    -0.43
    ánto
    -0.41
    makeText
    -0.40
    toprule
    -0.39
    ungkinan
    -0.39
    DebuggerNonUser
    -0.39
     <>",
    -0.39
     adequada
    -0.39
    Referencer
    -0.38
    TestingModule
    -0.38
    POSITIVE LOGITS
     cultivar
    0.51
     rapper
    0.51
    Autoritní
    0.49
     defaultstate
    0.49
     philosopher
    0.48
     taxon
    0.48
     kohdetta
    0.46
     wrestler
    0.43
    enchymal
    0.43
     entity
    0.43
    Activations Density 0.974%

    No Known Activations