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. 10-GEMMASCOPE-RES-16K
    6. 13316
    Prev
    Next
    INDEX
    Explanations

    the topic of computer programming or coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secondo
    -0.50
    Huh
    -0.47
    Het
    -0.45
     tắm
    -0.45
     lisse
    -0.43
     versus
    -0.43
    行動
    -0.42
    —
    -0.41
    рованного
    -0.41
     bizarre
    -0.41
    POSITIVE LOGITS
    enumi
    8.85
    enumii
    5.13
    BeginContext
    1.47
     MainAxisSize
    1.30
    OGND
    1.29
    Geplaatst
    1.29
     CreateTagHelper
    1.28
     AssemblyCompany
    1.27
    CloseOperation
    1.26
    ValueStyle
    1.26
    Activations Density 0.006%

    No Known Activations