© 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. 16-GEMMASCOPE-RES-16K
    11. 4822
    Prev
    Next
    INDEX
    Explanations

    questions and phrases related to understanding or defining concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Definition/explanation seeking

    np_acts-logits-general · gemini-2.0-flash

    questions about meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -1.11
     Shakspeare
    -1.09
     ſche
    -1.06
     ſtate
    -1.04
     reaſon
    -1.04
     ſmall
    -1.03
     Theſe
    -1.02
     greateſt
    -1.01
     Eſ
    -1.01
     ſever
    -1.00
    POSITIVE LOGITS
     "
    0.73
     meant
    0.67
     '
    0.65
     mean
    0.59
     to
    0.58
     p
    0.57
     “
    0.56
     «
    0.55
     
    0.54
     a
    0.52
    Activations Density 0.135%

    No Known Activations