© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 3302
    Prev
    Next
    INDEX
    Explanations

    phrases related to the presence of conditions and alternative options

    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
    expandindo
    -0.73
    Personendaten
    -0.65
     незавершена
    -0.61
    μφωνα
    -0.55
     himo
    -0.53
     externi
    -0.52
    dataclass
    -0.52
    Havolalar
    -0.51
     חיצוניים
    -0.51
    Personensuche
    -0.51
    POSITIVE LOGITS
     may
    3.36
    may
    2.56
     MAY
    2.00
     might
    1.91
     May
    1.85
    May
    1.83
     maybe
    1.63
    อาจ
    1.61
     mungkin
    1.59
    MAY
    1.56
    Activations Density 0.786%

    No Known Activations