Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 7741
    Prev
    Next
    INDEX
    Explanations

    references to personal ownership or customization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.81
    addPreferredGap
    -0.64
    bigsqcup
    -0.61
    DockStyle
    -0.58
    sqcup
    -0.58
    ILayout
    -0.57
    XmlAccessType
    -0.57
    rzej
    -0.56
    ennifer
    -0.56
     useState
    -0.55
    POSITIVE LOGITS
     own
    4.58
     Own
    3.99
    own
    3.88
    Own
    3.85
     OWN
    3.15
     eigenen
    2.84
     propia
    2.75
     eigene
    2.70
    OWN
    2.68
     propio
    2.56
    Activations Density 0.073%

    No Known Activations