© 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. 6508
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of quantity or extent

    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
    pozdrawiam
    -0.63
    ἱ
    -0.62
    zw
    -0.62
     Magee
    -0.61
     cei
    -0.61
    Pozdrawiam
    -0.61
    不断的
    -0.61
    spr
    -0.61
    Xoa
    -0.60
     vnto
    -0.60
    POSITIVE LOGITS
     much
    2.37
    much
    2.17
    Much
    2.10
     MUCH
    2.10
     Much
    2.02
     mucho
    1.69
    Mucho
    1.58
    mucho
    1.55
     mycket
    1.40
     viel
    1.38
    Activations Density 0.059%

    No Known Activations