© 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. 11-GEMMASCOPE-RES-16K
    11. 12846
    Prev
    Next
    INDEX
    Explanations

    elements related to safety and professional qualifications in a service context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onAttach
    -0.57
    hdashline
    -0.54
    culable
    -0.53
     Créez
    -0.53
    yntaxException
    -0.52
    ArgsConstructor
    -0.52
    monials
    -0.50
    __":
    -0.49
    ByExample
    -0.48
    PDIR
    -0.47
    POSITIVE LOGITS
    abestanden
    0.64
    InjectAttribute
    0.63
     вікі
    0.62
    CodedInputStream
    0.60
     useRouter
    0.57
    Glück
    0.57
     Дата
    0.54
     étrangère
    0.53
     féminine
    0.52
    Geplaatst
    0.52
    Activations Density 1.532%

    No Known Activations