© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4017
    Prev
    Next
    INDEX
    Explanations

    structured data representations related to tree views and menus

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    XML and HTML tags, especially those related to menus and tree structures.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.71
    ագրություններ
    -0.53
    fillType
    -0.51
     <>",
    -0.47
    Hentet
    -0.47
     pinulongan
    -0.45
     oprot
    -0.44
     CreateTagHelper
    -0.44
     TestBed
    -0.43
    Tikang
    -0.43
    POSITIVE LOGITS
     hierarchical
    0.59
    PreInfinity
    0.58
     hierarchy
    0.56
     hierarchies
    0.56
     hiér
    0.47
    tree
    0.45
     hierarch
    0.45
     tree
    0.45
     HIER
    0.42
    ammans
    0.41
    Activations Density 0.540%

    No Known Activations