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. 15052
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to the concept of "purposes."

    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
    VIAF
    -0.65
     Justice
    -0.55
     CWE
    -0.52
    kadang
    -0.52
    /***/
    -0.51
    POSURE
    -0.48
     عق
    -0.48
     cellpadding
    -0.47
    czegóły
    -0.47
    OwnProperty
    -0.46
    POSITIVE LOGITS
     purposes
    1.62
    purposes
    1.37
     Purposes
    1.20
     خارجية
    0.71
    parsedMessage
    0.71
    InSection
    0.69
    Билгалдахарш
    0.67
    matically
    0.67
    FundMe
    0.67
     referenties
    0.66
    Activations Density 0.075%

    No Known Activations