© 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. 7-GEMMASCOPE-RES-16K
    6. 15211
    Prev
    Next
    INDEX
    Explanations

    references to laws and rituals related to religious practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.75
    EDEFAULT
    -0.58
     HasFactory
    -0.56
     cherchés
    -0.55
     wireType
    -0.49
    cetes
    -0.47
    FunctionType
    -0.46
    Наде
    -0.46
    zenten
    -0.45
    intur
    -0.45
    POSITIVE LOGITS
    +#+#
    0.63
    AnchorStyles
    0.63
    AndEndTag
    0.62
    出版年
    0.61
    metingen
    0.58
    NgModule
    0.58
    HasAnnotation
    0.57
    EndContext
    0.57
    UpInside
    0.56
    DockStyle
    0.55
    Activations Density 0.091%

    No Known Activations