© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 5652
    Prev
    Next
    INDEX
    Explanations

    Java programming keywords and syntax elements, particularly those related to class definitions and user interface components in Android development

    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
     itſelf
    -1.09
     vixion
    -0.87
     myſelf
    -0.87
     pleaſure
    -0.85
    manship
    -0.83
     purpoſe
    -0.82
     themſelves
    -0.82
    ſelves
    -0.81
     SwitchCompat
    -0.80
     bekasi
    -0.79
    POSITIVE LOGITS
     تانيه
    0.53
    ècie
    0.50
    ,
    0.47
    毛病
    0.45
    </td>
    0.44
    ''
    0.44
     s
    0.43
     phẩm
    0.43
    makeConstraints
    0.42
    findpost
    0.42
    Activations Density 0.064%

    No Known Activations