Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9132
    Prev
    Next
    INDEX
    Explanations

    HTML and markup elements and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    กล
    -0.49
    Klar
    -0.48
     Akhir
    -0.48
    ApplicationTests
    -0.46
     тем
    -0.44
    abestanden
    -0.44
    absl
    -0.44
    weit
    -0.44
    +#+#
    -0.44
    Finally
    -0.43
    POSITIVE LOGITS
     lenker
    0.84
    IntoConstraints
    0.80
     resourceCulture
    0.78
    >{@
    0.75
     autorytatywna
    0.75
    Panamoan
    0.70
     ComVisible
    0.68
    Personensuche
    0.68
     Infórmanos
    0.65
    ագրություններ
    0.65
    Activations Density 0.283%

    No Known Activations