© 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. 30-GEMMASCOPE-RES-16K
    11. 12390
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to claims or statements in a legal context

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

    followed by subjunctive mood words

    np_acts-logits-general · gemini-2.0-flash

    legal and comparative conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     almohada
    -0.45
     capucha
    -0.44
     actualidad
    -0.44
     manicura
    -0.42
     Democrá
    -0.42
     Naciones
    -0.42
     toalla
    -0.41
     Beschluss
    -0.40
     Sicherung
    -0.40
    ándola
    -0.40
    POSITIVE LOGITS
    enderror
    0.69
    uxxxx
    0.65
     nahilalakip
    0.62
     noDo
    0.60
    SequentialGroup
    0.59
     CreateTagHelper
    0.59
     Zo
    0.57
    .*")]
    0.56
    >{@
    0.56
    ellido
    0.55
    Activations Density 6.165%

    No Known Activations