© 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. 15332
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge or familiarity, particularly in relation to public perception or status

    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
    htë
    -0.51
     initialState
    -0.50
    過的
    -0.50
    manjaro
    -0.50
     sockaddr
    -0.49
     normally
    -0.48
    uary
    -0.47
     least
    -0.47
    clearfix
    -0.47
    εν
    -0.47
    POSITIVE LOGITS
    WidgetItem
    0.74
     المعيارى
    0.72
    featureID
    0.68
    存于互联网档案馆
    0.66
    RegressionTest
    0.65
    .*")]
    0.62
    tagHelperRunner
    0.61
     transférez
    0.61
     wikipagina
    0.59
     विश्वसनीयता
    0.59
    Activations Density 0.112%

    No Known Activations