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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105220
    Prev
    Next
    INDEX
    Explanations

    instances of quoted speech or cited materials in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     or
    -0.43
    iz
    -0.36
     and
    -0.36
    CDCl
    -0.36
    ub
    -0.34
    har
    -0.34
    og
    -0.34
    or
    -0.34
    StateManager
    -0.34
    pra
    -0.33
    POSITIVE LOGITS
    httphttps
    0.94
     AssemblyTitle
    0.77
     <<<<<<<<<<<<<<
    0.73
    ✨:
    0.68
    setVerticalGroup
    0.68
    VersionUID
    0.66
     שוליים
    0.65
    enumi
    0.64
    期刊论文
    0.64
    NUMX
    0.63
    Activations Density 0.022%

    No Known Activations