Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9159
    Prev
    Next
    INDEX
    Explanations

    references to actions or events involving police or judicial procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bieber
    -0.47
    ệc
    -0.47
    rens
    -0.41
    XtraGrid
    -0.40
    ToFile
    -0.39
     zó
    -0.38
     esto
    -0.38
     prič
    -0.38
    なこと
    -0.38
    ğaz
    -0.37
    POSITIVE LOGITS
     esternos
    0.87
     authorities
    0.84
     Paglinawan
    0.84
     resourceCulture
    0.82
     către
    0.82
    TypedDataSet
    0.81
    XmlAccessorType
    0.81
    httphttps
    0.78
     فريبيس
    0.77
     transférez
    0.76
    Activations Density 0.435%

    No Known Activations