Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 8662
    Prev
    Next
    INDEX
    Explanations

    exclamatory, heavily capitalized headline and slogan-like phrases with bold, propagandistic or emphatic language.

    oai_token-act-pair · o3-miniTriggered by @yemengyus1

    elements related to technical specifications and definitions in programming or data structure contexts

    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
    ÁF
    -0.21
    Fordítás
    -0.20
    ]='\
    -0.20
    ENOMEM
    -0.19
    എ
    -0.19
    PSK
    -0.18
    EIO
    -0.18
    CESO
    -0.18
    ]<<"
    -0.18
    GTC
    -0.17
    POSITIVE LOGITS
     BACK
    0.63
     OVER
    0.62
     NIGHT
    0.61
     WATER
    0.61
     LAST
    0.60
     FOR
    0.60
     GOOD
    0.60
     WORK
    0.60
     THE
    0.60
     POINT
    0.60
    Activations Density 44.233%

    No Known Activations