© 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. 6-GEMMASCOPE-RES-16K
    11. 5895
    Prev
    Next
    INDEX
    Explanations

    phrases indicating constancy or a recurring theme

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Географи
    -0.59
     singolo
    -0.52
    躇
    -0.50
     entreprise
    -0.45
    twimg
    -0.44
    cloudf
    -0.44
     Hurt
    -0.44
     ugy
    -0.43
     domés
    -0.42
    zondere
    -0.41
    POSITIVE LOGITS
    fromnode
    0.64
    相変わらず
    0.63
    Eres
    0.63
    RepeatedField
    0.63
    Usual
    0.61
    minton
    0.61
     gewohnt
    0.61
     kaarangay
    0.60
     Roskov
    0.60
     Drapeau
    0.60
    Activations Density 0.144%

    No Known Activations