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. 4266
    Prev
    Next
    INDEX
    Explanations

    the presence of variations of the word “Le” in various forms and contexts

    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
    findpost
    -0.93
    /*
    -0.81
    eabouts
    -0.80
     Herrick
    -0.79
    guous
    -0.76
    DotNetBar
    -0.75
    --}}
    -0.72
    LikeLike
    -0.71
     Fland
    -0.71
     Bahnhof
    -0.70
    POSITIVE LOGITS
     LE
    1.23
    Le
    1.22
     Leighton
    1.18
    LE
    1.18
    le
    1.16
     Le
    1.14
     Leona
    1.09
     Leandro
    1.08
     Leicestershire
    1.07
     le
    1.04
    Activations Density 0.125%

    No Known Activations