© 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. 2514
    Prev
    Next
    INDEX
    Explanations

    repeated or contrasting elements within contexts or structures

    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
    yntaxException
    -1.06
    GraphicsUnit
    -0.85
     дописавши
    -0.84
     Савезне
    -0.83
    tvguidetime
    -0.82
    PMailer
    -0.79
    abetes
    -0.79
    
    -0.78
    oredCriteria
    -0.78
    VersionUID
    -0.78
    POSITIVE LOGITS
     same
    0.73
     as
    0.63
    same
    0.59
    Same
    0.54
     kuin
    0.52
     than
    0.51
     Same
    0.51
     you
    0.51
     that
    0.48
     but
    0.48
    Activations Density 0.209%

    No Known Activations