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. 25-GEMMASCOPE-RES-16K
    6. 3863
    Prev
    Next
    INDEX
    Explanations

    the presence of names or titles, specifically those starting with the letter 'F'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElementXpaths
    -0.60
     '{@
    -0.58
    ंदीखरीदारी
    -0.54
     useRef
    -0.52
     cover
    -0.52
    ள்
    -0.50
    Viited
    -0.50
    InitVars
    -0.50
     AssemblyVersion
    -0.49
     CreateTagHelper
    -0.48
    POSITIVE LOGITS
     propOrder
    0.61
     intptr
    0.55
     FetchType
    0.54
    centralwidget
    0.53
    httphttps
    0.52
     defStyle
    0.51
    didSet
    0.48
     defStyleAttr
    0.48
     Familienname
    0.47
    arkas
    0.47
    Activations Density 0.437%

    No Known Activations