© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 11874
    Prev
    Next
    INDEX
    Explanations

    terms related to educational institutions and their administrative roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.80
     الحره
    -0.78
     nahilalakip
    -0.76
    XmlAccessType
    -0.75
    ArgsConstructor
    -0.73
    $_['
    -0.70
     invokingState
    -0.69
    AndEndTag
    -0.67
     Roskov
    -0.66
    TagMode
    -0.65
    POSITIVE LOGITS
     löyty
    0.46
     scuole
    0.45
     endast
    0.44
     colegio
    0.44
    ac
    0.43
     leerlingen
    0.42
     Ensino
    0.42
     ragione
    0.42
     scolas
    0.42
     élèves
    0.42
    Activations Density 0.068%

    No Known Activations