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. 25-GEMMASCOPE-RES-16K
    6. 359
    Prev
    Next
    INDEX
    Explanations

    connections and collaborations in the art market, particularly between Chinese and Western entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.52
     OFDb
    -0.50
    <bos>
    -0.48
    Vidite
    -0.47
    فحه
    -0.45
    ագրություններ
    -0.45
    mui
    -0.45
    InitVars
    -0.44
    Matchers
    -0.43
    typeorm
    -0.43
    POSITIVE LOGITS
     Ar
    3.56
    Ar
    3.32
     ar
    3.04
     AR
    2.79
    ar
    2.32
    AR
    2.30
     Ар
    2.28
    Ар
    2.06
     ар
    1.99
     Arb
    1.76
    Activations Density 0.651%

    No Known Activations