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. 15912
    Prev
    Next
    INDEX
    Explanations

    mappings and assignments in programming languages

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

    PHP code snippets

    np_acts-logits-general · gemini-2.0-flash

    PHP `foreach` loops and variables

    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
    ])));
    -0.51
    Jeez
    -0.49
    apura
    -0.47
    
    -0.46
    المشاركات
    -0.45
    τυχ
    -0.45
    λλά
    -0.45
    Tembelea
    -0.45
    '|
    -0.44
    plass
    -0.43
    POSITIVE LOGITS
     NavController
    0.82
    djangoproject
    0.79
     geslacht
    0.75
    BufferException
    0.72
     Wikimedijinoj
    0.68
     wikipagina
    0.66
    NewUrlParser
    0.66
     ویکی‌پدیای
    0.64
     doInBackground
    0.60
    CodeAttribute
    0.60
    Activations Density 0.063%

    No Known Activations