© 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. 8-GEMMASCOPE-RES-16K
    6. 8951
    Prev
    Next
    INDEX
    Explanations

    terms related to legal advice and personal injury law

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الإنجليزية
    -0.61
     paradox
    -0.59
     fini
    -0.58
     []:
    -0.51
    Activité
    -0.48
     createState
    -0.48
    abstractmethod
    -0.48
     dần
    -0.47
    astra
    -0.47
     Hirst
    -0.47
    POSITIVE LOGITS
    ########.
    0.67
    ViewImports
    0.62
    XmlAccessType
    0.59
    ьаж
    0.59
    Derbyniad
    0.59
    expandindo
    0.54
     Settle
    0.51
     Lublin
    0.51
     Semarang
    0.49
    patient
    0.48
    Activations Density 0.203%

    No Known Activations