© 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. 24-GEMMASCOPE-RES-16K
    11. 2563
    Prev
    Next
    INDEX
    Explanations

    locations or contexts specified by the preposition "in"

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

    "in" followed by a preposition/noun

    np_acts-logits-general · gemini-2.0-flash

    in addition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    紹介します
    -0.67
    考える
    -0.65
    美国
    -0.60
    狙
    -0.59
     verrez
    -0.58
    principalTable
    -0.56
    urlopen
    -0.55
    Viitteet
    -0.55
    中国
    -0.54
    目指
    -0.54
    POSITIVE LOGITS
     addition
    1.33
     accordance
    1.32
     terms
    1.28
     relation
    1.24
     spite
    1.19
     lieu
    1.19
     conjunction
    1.19
     order
    1.12
     regards
    1.03
    jectable
    0.99
    Activations Density 1.171%

    No Known Activations