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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12765
    Prev
    Next
    INDEX
    Explanations

    technical terms related to surface treatments and mechanical structures

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

    Geometric patterns or textures

    np_acts-logits-general · gemini-2.0-flash

    surface textures and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    ValueStyle
    -0.75
    GOTREF
    -0.65
    BeginContext
    -0.59
    StoryboardSegue
    -0.58
     الرياضيه
    -0.57
    ьаж
    -0.54
    +#+#
    -0.54
    AndEndTag
    -0.53
     createStore
    -0.53
    AccessFile
    -0.52
    POSITIVE LOGITS
     pattern
    0.53
     patterns
    0.49
     patterned
    0.47
     textured
    0.44
     mesh
    0.43
    pattern
    0.43
     grid
    0.40
     texture
    0.40
     interwoven
    0.40
     сет
    0.40
    Activations Density 0.912%

    No Known Activations