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. 8-GEMMASCOPE-RES-16K
    6. 11094
    Prev
    Next
    INDEX
    Explanations

    code-related variables and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResumeLayout
    -0.76
    IsContent
    -0.71
     للمعارف
    -0.69
    UnusedPrivate
    -0.66
    GraphicsUnit
    -0.64
    AddHtmlAttribute
    -0.64
    DebuggerNonUser
    -0.63
    ]='\
    -0.62
     Infórmanos
    -0.62
     mxArray
    -0.60
    POSITIVE LOGITS
    ьаж
    0.71
    Diweddarwch
    0.61
     fillers
    0.58
     basses
    0.55
     Centurion
    0.54
     Secular
    0.54
     deschis
    0.54
    يكب
    0.53
     correspondents
    0.51
    rinhos
    0.51
    Activations Density 0.376%

    No Known Activations