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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 1202
    Prev
    Next
    INDEX
    Explanations

    HTML-related elements and tags used in web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -1.29
    +#+#
    -1.06
    ThroughAttribute
    -0.89
    Хьажоргаш
    -0.84
    expandindo
    -0.82
     المعيارى
    -0.79
    AsUp
    -0.79
     protoimpl
    -0.78
     kasarigan
    -0.78
    хьтан
    -0.78
    POSITIVE LOGITS
    ":[{
    0.79
    ISupport
    0.70
    álva
    0.63
    <!--[
    0.58
     Blau
    0.57
    setopt
    0.57
    $")
    0.55
    )(((
    0.55
    ?)
    0.54
    figcaption
    0.53
    Activations Density 0.102%

    No Known Activations