© 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. 13777
    Prev
    Next
    INDEX
    Explanations

    complex sentence structures and logical connectors

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

    Comes before discourse markers or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    hope and expectation

    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
    twimg
    -0.60
    Erreferentziak
    -0.53
    cloudfront
    -0.53
     snippetHide
    -0.52
    FlatAppearance
    -0.52
    RenderAtEndOf
    -0.52
    <?
    -0.51
    paq
    -0.48
     Explanation
    -0.48
     BoxFit
    -0.48
    POSITIVE LOGITS
     hopefully
    1.34
     Hopefully
    1.30
    Fingers
    1.27
    Hopefully
    1.23
    hopefully
    1.21
     Stay
    1.20
    fingers
    1.14
     Expect
    1.13
     Fingers
    1.12
    Stay
    1.10
    Activations Density 0.276%

    No Known Activations