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. 15220
    Prev
    Next
    INDEX
    Explanations

    content related to specific entities and their relationships, particularly in a technical or scientific context

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

    Hexadecimal codes and numbers appearing in text

    np_acts-logits-general · gemini-2.0-flash

    numbers and hexadecimal codes

    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
     tố
    -0.38
    SQLiteDatabase
    -0.35
     Post
    -0.34
     CGRectMake
    -0.34
     pl
    -0.34
    Received
    -0.31
     modern
    -0.31
     u
    -0.31
     audi
    -0.31
    imple
    -0.31
    POSITIVE LOGITS
     ویکی‌پدی
    0.83
     Paglinawan
    0.80
     resourceCulture
    0.78
     OMITBAD
    0.67
    httphttps
    0.64
    TypedDataSet
    0.60
     OFDb
    0.60
    хьтан
    0.60
    yntaxException
    0.59
    таратура
    0.59
    Activations Density 0.957%

    No Known Activations