© 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. 11-GEMMASCOPE-RES-16K
    6. 12747
    Prev
    Next
    INDEX
    Explanations

    specific identifiers or notable names within a scholarly context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    पया
    -0.76
    UrlResolution
    -0.72
     विश्वसनीयता
    -0.70
    \{\\
    -0.67
    CloseOperation
    -0.65
    ITERATURE
    -0.64
    GHIJKLM
    -0.64
    glEnd
    -0.61
    IVEREF
    -0.60
    .*/
    -0.59
    POSITIVE LOGITS
    InstanceState
    0.50
    contentLoaded
    0.47
    LookAnd
    0.45
    Diweddarwch
    0.42
    libft
    0.42
     typelib
    0.42
     Tenggara
    0.41
    cshtml
    0.41
    Gemeinden
    0.40
    CreateModel
    0.39
    Activations Density 0.158%

    No Known Activations