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. 23-GEMMASCOPE-RES-16K
    6. 12339
    Prev
    Next
    INDEX
    Explanations

    references to literary works and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElement
    -0.64
    LayoutConstraint
    -0.56
    adget
    -0.55
    Authors
    -0.53
     المعيارى
    -0.52
     beginnetje
    -0.51
     addSubview
    -0.50
    WidgetItem
    -0.50
     archaeologists
    -0.50
    Thunk
    -0.49
    POSITIVE LOGITS
     oeuvre
    1.02
     career
    0.87
     œuvre
    0.84
     works
    0.81
    oeuvre
    0.80
     style
    0.77
    career
    0.74
     ISNI
    0.72
     tuot
    0.71
     work
    0.70
    Activations Density 0.239%

    No Known Activations