© 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. 4472
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate active involvement or engagement in a situation

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

    Located at or near the side

    np_acts-logits-general · gemini-2.0-flash

    spatial positioning and watching

    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
    reszcie
    -0.54
     InputDecoration
    -0.46
    ışık
    -0.43
    XmlAccessType
    -0.42
    确
    -0.39
    Sklici
    -0.39
    Durée
    -0.39
    phosa
    -0.38
     einschließlich
    -0.38
     برانيه
    -0.38
    POSITIVE LOGITS
     sidelines
    1.47
     behind
    1.19
    behind
    1.16
     backstage
    1.15
     BEHIND
    1.13
     afar
    1.10
    Behind
    1.08
     Behind
    1.08
     sideline
    1.06
     nearby
    0.99
    Activations Density 0.190%

    No Known Activations