© 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. 16-GEMMASCOPE-RES-16K
    11. 1103
    Prev
    Next
    INDEX
    Explanations

    instructions related to cleaning or maintenance procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding or related to settings/levels

    np_acts-logits-general · gemini-2.0-flash

    heavy duty settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     throwable
    -0.51
    rested
    -0.51
     rest
    -0.49
     Regie
    -0.47
     Cornelius
    -0.47
     ducha
    -0.47
     csapat
    -0.47
    ளி
    -0.46
     velkommen
    -0.45
    éről
    -0.45
    POSITIVE LOGITS
     settings
    0.87
     Settings
    0.75
     SETTINGS
    0.73
    WriteBarrier
    0.72
     lowest
    0.70
     setting
    0.67
    settings
    0.65
     maxed
    0.61
    StartTag
    0.61
     highest
    0.61
    Activations Density 0.182%

    No Known Activations