© 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-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 13370
    Prev
    Next
    INDEX
    Explanations

    the presence of possessive contractions and informal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KURZBESCHREIBUNG
    -0.88
    ModelAdmin
    -0.83
    StructEnd
    -0.81
    󠁮
    -0.77
     Româ
    -0.77
    ">:
    -0.75
     AssemblyVersion
    -0.74
     שוליים
    -0.73
     pinulongan
    -0.72
     déput
    -0.72
    POSITIVE LOGITS
     [
    0.63
    .
    0.59
     co
    0.52
     um
    0.50
     Okay
    0.50
    EndContext
    0.50
     I
    0.49
     (
    0.49
    '
    0.48
     Oh
    0.48
    Activations Density 0.087%

    No Known Activations