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. 23-GEMMASCOPE-RES-16K
    6. 6438
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to repetition or reevaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResponseWriter
    -0.88
     AssemblyCulture
    -0.85
    RectangleBorder
    -0.78
     "..\..\
    -0.75
    Hozzáférés
    -0.75
     ویکی‌پدیا
    -0.75
    TagHelper
    -0.74
    شهاد
    -0.73
    GraphicsUnit
    -0.73
    ftagPool
    -0.72
    POSITIVE LOGITS
     secco
    0.56
     old
    0.51
    old
    0.49
    ฐ
    0.47
     viejos
    0.46
     havoc
    0.45
    __["
    0.45
     compte
    0.44
    getInteger
    0.44
    ing
    0.44
    Activations Density 0.536%

    No Known Activations