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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45859
    Prev
    Next
    INDEX
    Explanations

    concepts related to biological systems and their efficiencies, particularly in reference to sperm and cellular structures

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

    biological and natural design

    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-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
    enterOuterAlt
    -0.63
     يتيمه
    -0.51
     protoimpl
    -0.51
    expandindo
    -0.51
    ፩
    -0.50
     виправивши
    -0.49
    parsedMessage
    -0.49
    verwijspagina
    -0.48
     slideshow
    -0.48
    extAlignment
    -0.45
    POSITIVE LOGITS
     совершен
    0.41
    natural
    0.40
     marvel
    0.40
     perfeita
    0.40
    nature
    0.39
    perfect
    0.39
     biologic
    0.38
    design
    0.38
    mar
    0.37
     biological
    0.37
    Activations Density 0.104%

    No Known Activations