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. 11651
    Prev
    Next
    INDEX
    Explanations

    occurrences of the special character 'Ã'

    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
     تضيفلها
    -0.82
    contentLoaded
    -0.72
    addCriterion
    -0.65
     سكانية
    -0.63
    principalTable
    -0.62
    MLLoader
    -0.61
    ContentAsync
    -0.61
     lele
    -0.61
     comuniques
    -0.60
     незавершена
    -0.59
    POSITIVE LOGITS
     �
    0.81
    �
    0.56
    UInt
    0.45
     ��
    0.45
     zák
    0.45
    digm
    0.44
     attiva
    0.44
     '&#
    0.44
    Arm
    0.44
     giuri
    0.43
    Activations Density 0.264%

    No Known Activations