© 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. 2-GEMMASCOPE-RES-16K
    6. 1990
    Prev
    Next
    INDEX
    Explanations

    items related to hyperlinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    -1.01
     Monfieur
    -0.93
     ſever
    -0.83
    cabulary
    -0.83
     ſeveral
    -0.82
     theſe
    -0.82
     myſelf
    -0.79
     initComponents
    -0.78
     ſmall
    -0.78
     uſed
    -0.78
    POSITIVE LOGITS
     Link
    3.49
    link
    3.42
    Link
    3.42
     link
    3.40
     LINK
    3.12
    LINK
    2.95
     links
    2.78
    links
    2.60
     Links
    2.57
    Links
    2.44
    Activations Density 0.044%

    No Known Activations