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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 30070
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory compliance language

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

    prevented items, similar usage, target prosecutions

    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
    Toast
    -0.43
     TV
    -0.41
     Toast
    -0.40
     rame
    -0.40
     good
    -0.40
     Bear
    -0.40
     gypsy
    -0.39
     toast
    -0.39
     Tel
    -0.39
     great
    -0.39
    POSITIVE LOGITS
    RenderAtEndOf
    0.66
    +#+#
    0.58
    BagConstraints
    0.49
     budou
    0.49
     künftig
    0.48
    fromnode
    0.47
     prohibits
    0.47
    osexuality
    0.47
    новниш
    0.46
    principalColumn
    0.45
    Activations Density 0.039%

    No Known Activations