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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 10253
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "something."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.81
    日閲覧
    -0.75
    titian
    -0.73
    mejores
    -0.72
    zbęd
    -0.71
     xanth
    -0.71
    chließend
    -0.71
    prefixer
    -0.66
     Lait
    -0.66
    зоры
    -0.65
    POSITIVE LOGITS
     something
    1.75
    Something
    1.68
     Something
    1.65
    something
    1.65
     SOMETHING
    1.54
    ETHING
    1.53
     somethin
    1.38
    Somebody
    1.37
     somebody
    1.27
     else
    1.23
    Activations Density 0.089%

    No Known Activations