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. 24-GEMMASCOPE-RES-16K
    6. 12829
    Prev
    Next
    INDEX
    Explanations

    emphasized expressions and assessments of quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following intensifiers

    np_acts-logits-general · gemini-2.0-flash

    intensified descriptions with strong sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    мии
    -0.47
    втра
    -0.43
    intellij
    -0.43
    signIn
    -0.43
    twimg
    -0.42
     atos
    -0.42
     seba
    -0.41
    atação
    -0.41
     ritro
    -0.40
     initiator
    -0.39
    POSITIVE LOGITS
     surprised
    1.01
     impressed
    0.98
     shocked
    0.96
     disappointed
    0.95
     excited
    0.93
     happy
    0.90
     amazed
    0.88
     thrilled
    0.88
    StoryboardSegue
    0.87
     pleased
    0.87
    Activations Density 0.295%

    No Known Activations