© 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. 4168
    Prev
    Next
    INDEX
    Explanations

    references to legendary or mythical figures and themes related to power

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

    followed by punctuation or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    programming, SQL, and methods

    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
    awtextra
    -0.63
    HasForeignKey
    -0.62
    \{\\
    -0.62
     propOrder
    -0.61
    DeleteBehavior
    -0.55
    بوابة
    -0.54
    })}\
    -0.54
    '),
    -0.52
    )))
    -0.52
    NewUrlParser
    -0.51
    POSITIVE LOGITS
     everybody
    0.66
     oneself
    0.64
     bibliographical
    0.64
     again
    0.60
     somebody
    0.60
     be
    0.59
     comprise
    0.57
     owing
    0.56
    Somebody
    0.56
     asemenea
    0.55
    Activations Density 0.164%

    No Known Activations