© 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. 10-GEMMASCOPE-RES-16K
    6. 13587
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating transformative change or revolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    middels
    -0.49
     onCancelled
    -0.49
     Se
    -0.46
     cháu
    -0.46
    {.
    -0.44
     gebre
    -0.42
    ="{{
    -0.42
     EXERCISE
    -0.42
    Se
    -0.40
    hot
    -0.40
    POSITIVE LOGITS
     Normdatei
    0.90
     revolution
    0.90
     redefine
    0.82
     breakthrough
    0.78
    Personendaten
    0.76
     redefined
    0.75
    تقاوى
    0.73
    Revolution
    0.73
     Revolution
    0.72
    revolution
    0.72
    Activations Density 0.202%

    No Known Activations