© 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. 17-GEMMASCOPE-RES-16K
    6. 10476
    Prev
    Next
    INDEX
    Explanations

    specific chemical compounds and their derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    m
    -0.81
    r
    -0.67
    l
    -0.67
    ms
    -0.67
    ming
    -0.64
    ling
    -0.63
    ness
    -0.63
    ramine
    -0.61
    ly
    -0.61
    ram
    -0.60
    POSITIVE LOGITS
     pleaſure
    1.02
     purpoſe
    0.95
     myſelf
    0.95
     poffe
    0.93
     Dooley
    0.88
     miſ
    0.87
     raiſ
    0.87
     againſt
    0.85
     ſtate
    0.85
     Malo
    0.85
    Activations Density 0.850%

    No Known Activations