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. 11-GEMMASCOPE-RES-16K
    6. 6921
    Prev
    Next
    INDEX
    Explanations

    concepts related to blessings and well-being

    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
    RenderAtEndOf
    -0.76
    fromnode
    -0.72
     Wiktionnaire
    -0.71
    MigrationBuilder
    -0.69
     Numerade
    -0.68
    tanleria
    -0.66
    awtextra
    -0.66
     שוליים
    -0.66
    XmlAccessType
    -0.65
     виправивши
    -0.63
    POSITIVE LOGITS
     rowspan
    0.57
    @
    0.46
     stuck
    0.44
    !
    0.43
    googleapis
    0.42
     Präsidenten
    0.41
    </i>
    0.41
    URIComponent
    0.40
    ps
    0.39
    jad
    0.39
    Activations Density 0.287%

    No Known Activations