© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8428
    Prev
    Next
    INDEX
    Explanations

    references to the second-person pronoun "you" and its variations

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

    "You" followed by certain auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    you followed by a verb

    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
    RenderAtEndOf
    -0.76
     ProtoMessage
    -0.65
    localctx
    -0.59
    RegistryLite
    -0.59
    ◀
    -0.56
    الحياه
    -0.56
    usercontent
    -0.55
    webElementXpaths
    -0.54
     trast
    -0.53
     trattano
    -0.53
    POSITIVE LOGITS
     deserve
    0.68
    abestanden
    0.68
    tvguidetime
    0.62
    ")->
    0.61
     May
    0.59
    Tuber
    0.59
     can
    0.59
     Tube
    0.58
     may
    0.56
     too
    0.55
    Activations Density 0.095%

    No Known Activations