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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9114
    Prev
    Next
    INDEX
    Explanations

    legal and procedural terminology related to amending complaints and ensuring due process

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

    correcting or resolving

    np_acts-logits-general · gemini-2.0-flash

    resolve issues

    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
    tagHelperRunner
    -0.68
     betweenstory
    -0.53
    TextHelper
    -0.51
    ⓧ
    -0.51
    SequentialGroup
    -0.51
     perche
    -0.50
    ſelves
    -0.50
    авто
    -0.49
    hetamine
    -0.47
     myſelf
    -0.47
    POSITIVE LOGITS
     corrected
    0.50
     correction
    0.48
     corrective
    0.46
     الرياضيه
    0.44
     corrections
    0.43
    corrected
    0.42
     resolve
    0.39
     remedied
    0.39
    修正
    0.39
     rectify
    0.39
    Activations Density 0.425%

    No Known Activations