© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 10998
    Prev
    Next
    INDEX
    Explanations

    terms indicating expertise and specialized knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Naidu
    -0.82
    cauc
    -0.78
    TypedDataSet
    -0.76
     Hogarth
    -0.76
    writerow
    -0.73
     Pilate
    -0.73
    łasz
    -0.71
     cometh
    -0.70
    parsedMessage
    -0.69
     createSlice
    -0.68
    POSITIVE LOGITS
     experts
    1.30
     expert
    1.22
     Expert
    1.22
     Experts
    1.13
    Expert
    1.13
     expertise
    1.11
     EXPERT
    1.11
    Expertise
    1.05
    Experts
    1.03
    expert
    1.02
    Activations Density 0.053%

    No Known Activations