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. 7862
    Prev
    Next
    INDEX
    Explanations

    significant legal terms and conditions related to motion for summary judgment

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

    Tokens starting with "AP" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    append, AP, apparatus, Appellant

    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
     فريبيس
    -0.71
     HasFactory
    -0.69
    脚注の使い方
    -0.64
    GraphicsUnit
    -0.64
    viaf
    -0.64
     Kig
    -0.63
     Mohr
    -0.63
     Lorraine
    -0.62
    ---*/
    -0.61
     Hurley
    -0.60
    POSITIVE LOGITS
     AP
    1.87
     Ap
    1.80
    AP
    1.63
     App
    1.59
    Ap
    1.59
     ap
    1.58
    App
    1.56
     APP
    1.42
     Appel
    1.42
    APP
    1.41
    Activations Density 0.375%

    No Known Activations