© 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. 6467
    Prev
    Next
    INDEX
    Explanations

    instances of the word "following."

    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
     appelez
    -0.53
    二是
    -0.52
    遭到
    -0.51
     ahogy
    -0.50
    已是
    -0.48
    HasOne
    -0.47
     starb
    -0.46
    autor
    -0.46
     &
    -0.46
    ૂ
    -0.46
    POSITIVE LOGITS
     following
    2.08
    following
    1.78
     seguinte
    1.68
     suivante
    1.58
     seguintes
    1.54
     FOLLOWING
    1.53
     siguiente
    1.50
     följande
    1.49
     siguientes
    1.49
     følgende
    1.44
    Activations Density 0.154%

    No Known Activations