© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1191
    Prev
    Next
    INDEX
    Explanations

    phrases related to reaching goals or targets

    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
    vian
    -0.52
     üzerinde
    -0.48
    usercontent
    -0.48
     groß
    -0.46
     Packs
    -0.45
    omenclature
    -0.45
     closely
    -0.44
    sinon
    -0.44
     Primero
    -0.43
     heavily
    -0.43
    POSITIVE LOGITS
     reach
    1.74
     reached
    1.67
     reaches
    1.59
    reached
    1.54
    Reaching
    1.54
     Reach
    1.52
    reach
    1.51
    Reach
    1.50
     reaching
    1.49
     Reaching
    1.42
    Activations Density 0.377%

    No Known Activations