© 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. 19-GEMMASCOPE-RES-16K
    11. 11904
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or well-wishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.58
    thâu
    -0.56
    UnknownFieldSet
    -0.56
     WebDriverWait
    -0.53
    ﷺ
    -0.52
    XmlAccessorType
    -0.51
     незавершена
    -0.51
    Wird
    -0.50
     modelAndView
    -0.49
     lisesi
    -0.48
    POSITIVE LOGITS
     reiterate
    0.87
     remind
    0.84
     clarify
    0.77
     mention
    0.76
     briefly
    0.69
     emphasize
    0.66
     emphasise
    0.66
     reminding
    0.66
     warn
    0.65
    remind
    0.65
    Activations Density 0.167%

    No Known Activations