© 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. 8-GEMMASCOPE-RES-16K
    6. 4474
    Prev
    Next
    INDEX
    Explanations

    statements of opinion or subjective assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -1.60
     Efq
    -1.59
     myſelf
    -1.54
     Chriftian
    -1.47
     Jefus
    -1.45
     himſelf
    -1.43
     raiſ
    -1.40
     fevere
    -1.40
     themſelves
    -1.39
     Houſe
    -1.38
    POSITIVE LOGITS
     a
    1.07
     the
    1.00
     its
    0.89
     not
    0.86
     
    0.86
     an
    0.80
     The
    0.79
     is
    0.79
     all
    0.78
    s
    0.77
    Activations Density 0.159%

    No Known Activations