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

    Neuronpedia

    APICircuit 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. 11-GEMMASCOPE-RES-16K
    6. 6114
    Prev
    Next
    INDEX
    Explanations

    key verbs and phrases indicating necessity, observation, and progress in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.56
    InitVars
    -0.53
    чка
    -0.53
    েই
    -0.52
    исленность
    -0.51
     half
    -0.51
    inFile
    -0.51
     ostr
    -0.51
    Palmar
    -0.50
    Composable
    -0.50
    POSITIVE LOGITS
    RenderAtEndOf
    0.76
    ValueStyle
    0.74
     Infórmanos
    0.73
    XmlAccessType
    0.72
     CreateTagHelper
    0.72
    multer
    0.69
    riwal
    0.67
    PRNewswire
    0.65
     desconhe
    0.60
    óngase
    0.60
    Activations Density 0.450%

    No Known Activations