© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1817
    Prev
    Next
    INDEX
    Explanations

    expressions of need or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XtraEditors
    -1.08
     themſelves
    -0.99
    ViewFeatures
    -0.94
    colhead
    -0.87
    iedenen
    -0.85
     becauſe
    -0.85
     againſt
    -0.85
    )";
    -0.83
    orate
    -0.81
     ſtate
    -0.81
    POSITIVE LOGITS
     need
    2.15
     Need
    1.90
    NEED
    1.82
     NEED
    1.81
    need
    1.79
     needs
    1.78
    Need
    1.78
     needed
    1.52
     Needs
    1.45
     NEEDS
    1.44
    Activations Density 0.101%

    No Known Activations