© 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. 18-GEMMASCOPE-RES-16K
    6. 9478
    Prev
    Next
    INDEX
    Explanations

    references to authority and decision-making within religious contexts

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

    Code, technical terms, or identifiers

    np_acts-logits-general · gemini-2.0-flash

    si2, release2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.64
    +#+
    -0.50
    qtype
    -0.50
     Chwiliwch
    -0.49
    Carcinogenicity
    -0.47
    bh
    -0.47
    brale
    -0.45
    бенок
    -0.44
    िये
    -0.44
    ymce
    -0.44
    POSITIVE LOGITS
     IndexPath
    0.68
    msgTypes
    0.60
    uxxxx
    0.60
     createStore
    0.58
    SBATCH
    0.56
    XmlSchema
    0.56
    ftagPool
    0.55
     chaînes
    0.55
    TextWatcher
    0.55
    IVEREF
    0.54
    Activations Density 0.033%

    No Known Activations