Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 14897
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there" and its variations, indicating presence or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CURIAM
    -0.52
     localObject
    -0.50
    プリング
    -0.50
    さっぱり
    -0.48
     herein
    -0.47
    зина
    -0.45
    epy
    -0.45
     khas
    -0.44
     createdAt
    -0.44
    Vendo
    -0.44
    POSITIVE LOGITS
     There
    1.29
    There
    1.26
     there
    1.20
    there
    1.08
    THERE
    0.91
     υπάρχ
    0.89
     THERE
    0.89
    "]));
    0.72
     existem
    0.71
    πάρχ
    0.71
    Activations Density 0.151%

    No Known Activations