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. 3-GEMMASCOPE-RES-16K
    6. 10223
    Prev
    Next
    INDEX
    Explanations

    instances of the word "where."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vance
    -0.63
    ArrowToggle
    -0.61
     Betts
    -0.61
     Bullock
    -0.60
     Schuh
    -0.58
     Haley
    -0.58
    सन्दर्भ
    -0.58
     Ashby
    -0.57
     initData
    -0.56
     Emery
    -0.56
    POSITIVE LOGITS
     where
    2.41
    where
    2.21
     WHERE
    2.05
     Where
    2.04
    Where
    2.02
    WHERE
    1.89
     donde
    1.69
     où
    1.65
    Donde
    1.62
     Où
    1.55
    Activations Density 0.066%

    No Known Activations