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. 7-GEMMASCOPE-RES-16K
    6. 6416
    Prev
    Next
    INDEX
    Explanations

    function calls related to view inflation in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteLiteral
    -0.65
     bar
    -0.57
     \
    -0.52
     Pre
    -0.51
    bar
    -0.48
    Pyx
    -0.47
    al
    -0.47
    os
    -0.46
     W
    -0.46
    stry
    -0.45
    POSITIVE LOGITS
     GenerationType
    1.23
     jsPsych
    1.11
    inflate
    1.07
     kaarangay
    1.04
    
    1.03
    DataAnnotations
    0.98
     nakalista
    0.95
    rungsseite
    0.93
    DialogInterface
    0.92
    AccessorTable
    0.92
    Activations Density 0.005%

    No Known Activations