© 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. 3-GEMMASCOPE-RES-16K
    11. 12230
    Prev
    Next
    INDEX
    Explanations

    words indicating a sequence or list of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fraid
    -0.60
    seits
    -0.60
     ahogy
    -0.60
    ítja
    -0.58
    groet
    -0.56
     ویکی‌پدیا
    -0.55
    örté
    -0.55
    掂
    -0.55
     recevez
    -0.55
    anus
    -0.55
    POSITIVE LOGITS
     following
    2.30
    following
    1.98
     FOLLOWING
    1.67
     seguinte
    1.66
     suivante
    1.60
     siguiente
    1.58
     siguientes
    1.56
     Following
    1.55
     följande
    1.55
    Following
    1.55
    Activations Density 0.099%

    No Known Activations