© 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. 7-GEMMASCOPE-RES-16K
    6. 11364
    Prev
    Next
    INDEX
    Explanations

    functions related to string manipulation, particularly those that handle case conversion and trimming

    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
    うちに
    -0.48
    用に
    -0.47
    менно
    -0.45
    op
    -0.44
    込めて
    -0.43
    serviceWorker
    -0.43
     comprome
    -0.43
     temu
    -0.43
     निय
    -0.42
    ारे
    -0.42
    POSITIVE LOGITS
     تضيفلها
    1.11
    ToUpper
    1.10
    ToLower
    1.06
    toLowerCase
    1.05
    NewGuid
    0.95
    toUpperCase
    0.92
    PerformLayout
    0.92
    Trim
    0.91
    trim
    0.90
     Trim
    0.83
    Activations Density 0.045%

    No Known Activations