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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11656
    Prev
    Next
    INDEX
    Explanations

    combinations of variables and their relationships in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.55
    fromnode
    -0.50
    Viitteet
    -0.49
     <>",
    -0.47
    thenReturn
    -0.47
    parsedMessage
    -0.42
     estekak
    -0.42
     omge
    -0.41
    detectChanges
    -0.41
    səhifə
    -0.41
    POSITIVE LOGITS
    mainloop
    0.41
    Modul
    0.37
     Islands
    0.37
     تضيفلها
    0.37
     Tasks
    0.36
     solicit
    0.36
     dAtA
    0.35
    InputTagHelper
    0.35
    ToolStrip
    0.35
    ípio
    0.35
    Activations Density 0.675%

    No Known Activations