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. 6852
    Prev
    Next
    INDEX
    Explanations

    expressions of necessity or requirements

    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
     strerror
    -0.65
    XtraEditors
    -0.62
    сылкі
    -0.61
    colhead
    -0.57
     textStatus
    -0.57
    ViewFeatures
    -0.55
     Spazier
    -0.52
     ciascuno
    -0.51
    ViewImports
    -0.51
    CloseOperation
    -0.50
    POSITIVE LOGITS
     need
    4.47
    need
    3.83
     Need
    3.77
    Need
    3.59
     needs
    3.49
     NEED
    3.40
    NEED
    3.28
     Needs
    3.02
    needs
    2.99
    Needs
    2.83
    Activations Density 0.071%

    No Known Activations