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. 6066
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and mathematical notation

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

    Mathematical equations or expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical inequalities and asymptotics

    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
     صوتيه
    -0.67
    terase
    -0.65
    bibitem
    -0.63
    YSTEM
    -0.58
    ESOME
    -0.58
    AllAfrica
    -0.57
    berfläche
    -0.57
    itemBuilder
    -0.56
    queryInterface
    -0.55
    LEncoder
    -0.55
    POSITIVE LOGITS
    CPtr
    0.63
     lemn
    0.57
     disambiguazione
    0.56
    ValueStyle
    0.50
    in
    0.49
    MENAFN
    0.47
     elettrica
    0.45
    HasBeenSet
    0.44
     œuvres
    0.43
    yntaxException
    0.43
    Activations Density 0.808%

    No Known Activations