© 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. 2-GEMMASCOPE-RES-16K
    11. 15371
    Prev
    Next
    INDEX
    Explanations

    terminology and references related to support, assistance, or funding in a research or academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vendido
    -0.57
    voyez
    -0.56
     misused
    -0.53
     drank
    -0.53
     lost
    -0.52
     caído
    -0.51
     dried
    -0.50
     resourceCulture
    -0.50
     crashed
    -0.49
     shew
    -0.49
    POSITIVE LOGITS
     aided
    1.60
     assisted
    1.60
     guided
    1.52
    assisted
    1.44
     inspired
    1.41
     Supported
    1.37
    Assisted
    1.37
     Assisted
    1.37
     Guided
    1.36
     supported
    1.35
    Activations Density 0.219%

    No Known Activations