© 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. 2961
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and terms related to differentiation and polynomial functions

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

    mathematical expressions and specific types of functions related to algebraic structures

    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
    WithMany
    -0.52
    ductors
    -0.52
     незавершена
    -0.51
     Paglinawan
    -0.49
    xaml
    -0.49
     الرياضيه
    -0.47
     Améli
    -0.47
    hilt
    -0.46
    Viited
    -0.46
     européennes
    -0.45
    POSITIVE LOGITS
    setVerticalGroup
    0.57
     Walkover
    0.56
     dec
    0.54
     vanishes
    0.54
     satisfies
    0.53
    ValueStyle
    0.53
     admits
    0.52
     scales
    0.51
     vanish
    0.51
     factor
    0.51
    Activations Density 1.439%

    No Known Activations