© 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. 25-GEMMASCOPE-RES-16K
    6. 3215
    Prev
    Next
    INDEX
    Explanations

    Special mathematical notation or symbols often used in complex equations and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -\
    -1.46
    ########.
    -0.82
    ют
    -0.77
    =\
    -0.69
    BASEPATH
    -0.62
    CROSSTALK
    -0.62
    ing
    -0.61
    IVEREF
    -0.61
     Wikispecies
    -0.60
     mxArray
    -0.59
    POSITIVE LOGITS
    utches
    0.53
    bion
    0.53
    modb
    0.52
    Victorian
    0.50
     AssemblyVersion
    0.48
    ArrowToggle
    0.48
     Downs
    0.48
    Ҭ
    0.47
    iment
    0.47
    angelo
    0.46
    Activations Density 0.923%

    No Known Activations