© 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. 5-GEMMASCOPE-RES-16K
    11. 3687
    Prev
    Next
    INDEX
    Explanations

    commands and instructions related to enabling or disabling features in software or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.63
    ↵
    -0.63
    /
    -0.60
    ?
    -0.56
    ,
    -0.52
     (
    -0.52
    (
    -0.52
     N
    -0.51
    l
    -0.50
    <eos>
    -0.50
    POSITIVE LOGITS
     disable
    2.23
     Disable
    1.96
    disable
    1.94
    Disable
    1.70
     disabling
    1.62
     disables
    1.48
     deactivate
    1.23
     DISABLE
    1.22
    DISABLE
    1.20
     Enable
    1.15
    Activations Density 0.035%

    No Known Activations