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. 11-GEMMASCOPE-RES-16K
    6. 14002
    Prev
    Next
    INDEX
    Explanations

    references to academic papers or authors in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kira
    -0.69
    Becker
    -0.68
     Sheeran
    -0.66
    <i>
    -0.65
     petal
    -0.65
    hift
    -0.64
     cérebro
    -0.64
    Teb
    -0.64
     Denny
    -0.62
     Edy
    -0.62
    POSITIVE LOGITS
     Vou
    1.16
     POU
    1.13
    hou
    1.12
     LOU
    1.11
     Kou
    1.07
     Cou
    1.06
    Shou
    1.05
    OU
    1.04
    OUG
    1.03
     gou
    1.02
    Activations Density 0.229%

    No Known Activations