© 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. 18-GEMMASCOPE-RES-16K
    11. 229
    Prev
    Next
    INDEX
    Explanations

    technical terms and notation related to statistical modeling and mathematics

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

    Mathematical or statistical notation/equations

    np_acts-logits-general · gemini-2.0-flash

    random variables and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdc
    -0.49
    ")));
    -0.46
    ()]
    -0.46
     Dance
    -0.45
    balleur
    -0.45
     comfor
    -0.44
    Билгалдахарш
    -0.44
    脚注の使い方
    -0.44
    }}/>
    -0.43
     Evolutionary
    -0.43
    POSITIVE LOGITS
     outcome
    0.70
     outcomes
    0.68
    Outcome
    0.67
     Outcome
    0.66
     random
    0.66
     Outcomes
    0.64
    Біографія
    0.64
    outcome
    0.60
     propOrder
    0.58
     Sist
    0.58
    Activations Density 1.958%

    No Known Activations