© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2909
    Prev
    Next
    INDEX
    Explanations

    elements that suggest claims or assertions about events or conditions, particularly regarding the legitimacy or authority of those claims

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

    preceding pronouns like "she," "he," or "they"

    np_acts-logits-general · gemini-2.0-flash

    time and circumstances for actions

    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
    them
    -2.15
     THEM
    -1.83
     Them
    -1.55
     them
    -1.53
    Them
    -1.44
    THEY
    -1.34
    they
    -1.33
     They
    -1.27
    him
    -1.18
    They
    -1.16
    POSITIVE LOGITS
    webElementXpaths
    1.02
     @"/
    0.77
    providedIn
    0.72
     &___
    0.69
     autorytatywna
    0.68
    MessageInfo
    0.68
    Jeografia
    0.64
     protoimpl
    0.62
    tagHelperRunner
    0.62
    localctx
    0.61
    Activations Density 0.551%

    No Known Activations