© 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. 10510
    Prev
    Next
    INDEX
    Explanations

    references to fashion and seasonal clothing styles

    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
     watermelon
    -0.59
    aclk
    -0.58
     Watermelon
    -0.56
     cref
    -0.55
     June
    -0.53
    JULY
    -0.53
     dàng
    -0.53
    iwisata
    -0.52
    uertos
    -0.52
     July
    -0.51
    POSITIVE LOGITS
     warmth
    1.18
     warm
    1.11
     warmest
    1.07
     Warm
    1.04
    Warm
    0.98
    warm
    0.97
     fleece
    0.97
     warming
    0.95
     warmer
    0.93
     warms
    0.92
    Activations Density 0.261%

    No Known Activations