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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10227
    Prev
    Next
    INDEX
    Explanations

    legal terminology and concepts related to law and evidence

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

    preceding verbs of possibility or necessity

    np_acts-logits-general · gemini-2.0-flash

    may have, which indicates, situation here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vectorielles
    -0.82
     transitioning
    -0.75
    脚注の使い方
    -0.75
     jobbet
    -0.74
     prioritized
    -0.74
     réfrig
    -0.73
    abestanden
    -0.72
    存于互联网档案馆
    -0.72
     otomatig
    -0.71
     prioritizing
    -0.70
    POSITIVE LOGITS
     skall
    0.70
     muß
    0.56
     furnish
    0.53
     doubtless
    0.52
     furnished
    0.51
    furn
    0.50
     procura
    0.49
    Надо
    0.49
     accords
    0.49
     /\.(
    0.48
    Activations Density 0.945%

    No Known Activations