© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 13638
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or possibility related to the concept of "something."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zbęd
    -0.78
    UnusedPrivate
    -0.76
    owohl
    -0.76
     Lait
    -0.73
    日閲覧
    -0.72
     Genoa
    -0.70
    curacy
    -0.69
     xanth
    -0.69
    zewod
    -0.69
     Tiz
    -0.67
    POSITIVE LOGITS
     something
    1.96
    something
    1.90
    Something
    1.89
     Something
    1.88
     SOMETHING
    1.68
    ETHING
    1.49
    Somebody
    1.48
     somethin
    1.48
     somebody
    1.40
    Someone
    1.37
    Activations Density 0.070%

    No Known Activations