© 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. 2-GEMMASCOPE-RES-16K
    11. 1805
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "do" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KEYCODE
    -0.64
    ậy
    -0.59
     kaarangay
    -0.57
    umman
    -0.56
    ########.
    -0.56
    shortcuts
    -0.54
     rozwiąz
    -0.54
     shouldBe
    -0.53
     attendu
    -0.52
     uncin
    -0.51
    POSITIVE LOGITS
     also
    0.68
     does
    0.68
     do
    0.67
     did
    0.64
     Tampoco
    0.62
     pernah
    0.62
    也沒有
    0.61
    确实
    0.61
    確實
    0.60
    mergeFrom
    0.59
    Activations Density 0.335%

    No Known Activations