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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2001
    Prev
    Next
    INDEX
    Explanations

    forms of self-expression and opinions regarding personal beliefs

    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
    UnknownFields
    -0.49
    |"
    -0.41
    unkel
    -0.41
     oprot
    -0.41
    wsgi
    -0.38
    tot
    -0.38
    industri
    -0.38
    Yikes
    -0.37
    endu
    -0.37
     Element
    -0.37
    POSITIVE LOGITS
     disambiguazione
    0.80
    LookAnd
    0.79
     initComponents
    0.69
     EconPapers
    0.69
     مشين
    0.66
     sumpay
    0.65
    elemField
    0.64
     Passer
    0.64
     jugement
    0.64
     defStyleAttr
    0.63
    Activations Density 0.139%

    No Known Activations