© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 4788
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal issues and governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avenge
    -0.56
    baha
    -0.54
    JpaRepository
    -0.54
     Arki
    -0.52
     отно
    -0.52
    wieś
    -0.49
    /**
    -0.49
    TextInputLayout
    -0.49
    altezza
    -0.48
    ordning
    -0.48
    POSITIVE LOGITS
    ValueStyle
    0.64
     lack
    0.58
     recent
    0.58
    lack
    0.57
    omic
    0.57
    expandindo
    0.56
    esez
    0.54
    IVEREF
    0.54
    Personendaten
    0.54
    ultades
    0.53
    Activations Density 0.509%

    No Known Activations