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. 9-GEMMASCOPE-RES-131K
    6. 25300
    Prev
    Next
    INDEX
    Explanations

    technical terminology and phrases related to computer programming or web development

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

    conversational interjections btw

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resolu
    -0.49
    ijing
    -0.48
    undering
    -0.47
    ower
    -0.47
    TagMode
    -0.47
    ilin
    -0.46
    くい
    -0.46
    ölkerung
    -0.45
     resolution
    -0.45
    ouro
    -0.45
    POSITIVE LOGITS
     brisk
    0.90
     tbh
    0.68
    brtc
    0.65
    MENAFN
    0.58
    prefixer
    0.52
     briskly
    0.51
     IRL
    0.49
    Tbh
    0.48
    iyaki
    0.47
    noscript
    0.43
    Activations Density 0.003%

    No Known Activations