© 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. 10-GEMMASCOPE-RES-16K
    6. 11979
    Prev
    Next
    INDEX
    Explanations

    structured data references or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verwijspagina
    -0.55
    tagHelperRunner
    -0.55
     perpétu
    -0.53
    存于互联网档案馆
    -0.53
     كومونز
    -0.47
     للمعارف
    -0.47
    winners
    -0.47
     للاسماء
    -0.46
     urbain
    -0.46
     sexuales
    -0.46
    POSITIVE LOGITS
     &___
    0.82
     useContext
    0.72
     useRef
    0.60
    uteria
    0.58
    enderror
    0.58
    <?=$
    0.56
    liferay
    0.56
    Géographie
    0.56
    __((
    0.54
    InitStructure
    0.53
    Activations Density 0.087%

    No Known Activations