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. 3-GEMMASCOPE-RES-16K
    6. 16229
    Prev
    Next
    INDEX
    Explanations

    pronouns and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ListItemIcon
    -0.64
    تقاوى
    -0.55
    WaitGroup
    -0.55
     &___
    -0.54
    LookAnd
    -0.54
    SMB
    -0.53
     Bö
    -0.52
    offsetof
    -0.52
     pygame
    -0.51
     WebApplication
    -0.50
    POSITIVE LOGITS
    Revenir
    0.64
     跳转至
    0.60
     trebui
    0.57
     labd
    0.56
    GenerationType
    0.53
     chiara
    0.52
     subtil
    0.51
     financeira
    0.51
    相当
    0.51
     Jungfrau
    0.51
    Activations Density 0.243%

    No Known Activations