© 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. 2-GEMMASCOPE-RES-16K
    11. 14758
    Prev
    Next
    INDEX
    Explanations

    words expressing positivity and admiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsContent
    -0.69
    gypti
    -0.64
     almeno
    -0.62
    Slf
    -0.62
     allegedly
    -0.60
     autora
    -0.60
    AdapterView
    -0.57
     silencio
    -0.55
    CacheManager
    -0.55
     Cassius
    -0.55
    POSITIVE LOGITS
     wonderful
    3.04
    wonderful
    2.76
    Wonderful
    2.57
     Wonderful
    2.56
     marvelous
    2.35
     marvellous
    2.18
     fantastic
    2.16
     fabulous
    2.05
     terrific
    2.04
     wonderfully
    2.02
    Activations Density 0.052%

    No Known Activations