© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 13991
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to" and phrases involving it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setDo
    -0.70
    ască
    -0.52
     should
    -0.48
    への
    -0.48
     and
    -0.45
     чему
    -0.45
    ępo
    -0.44
     общей
    -0.44
    广泛
    -0.43
     Should
    -0.43
    POSITIVE LOGITS
     myſelf
    1.04
     ſeveral
    0.84
     poffible
    0.82
     Monfieur
    0.81
     itſelf
    0.80
     raiſ
    0.79
    ^(@)
    0.77
     ſche
    0.76
    UnusedPrivate
    0.75
     ſmall
    0.75
    Activations Density 0.226%

    No Known Activations