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. 12-GEMMASCOPE-RES-16K
    6. 6210
    Prev
    Next
    INDEX
    Explanations

    references to specific experimental methods and materials used in scientific research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Helix list

    No Comments

    Negative Logits
    picasso
    -0.77
     препратки
    -0.74
     cáo
    -0.68
    ngdoc
    -0.68
    URLException
    -0.66
    bhan
    -0.66
     previa
    -0.65
    VersionUID
    -0.65
    TemporalType
    -0.64
    gunas
    -0.62
    POSITIVE LOGITS
    PhysRevD
    1.22
     DPR
    0.89
     DHS
    0.87
     Dn
    0.87
     DSS
    0.87
     DTS
    0.86
     Dink
    0.86
     DCA
    0.85
    getD
    0.85
     DPD
    0.85
    Activations Density 1.695%

    No Known Activations