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. 15-GEMMASCOPE-RES-16K
    6. 12838
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or wanting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CrossRef
    -0.93
     unknownFields
    -0.90
     esternos
    -0.87
     magasiner
    -0.86
     AssemblyCompany
    -0.84
    setVerticalGroup
    -0.83
    XtraEditors
    -0.81
    SourceChecksum
    -0.80
     initComponents
    -0.79
    ſelf
    -0.79
    POSITIVE LOGITS
     want
    1.33
     WANT
    1.27
     Wants
    1.17
     wants
    1.16
     wanted
    1.12
    want
    1.09
     Want
    1.09
    wants
    1.01
    WANT
    1.00
    Want
    0.99
    Activations Density 0.099%

    No Known Activations