© 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. 5-GEMMASCOPE-RES-16K
    6. 9750
    Prev
    Next
    INDEX
    Explanations

    names of orchestras and their conducting facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.64
     écoulé
    -0.60
    HomeAsUpEnabled
    -0.58
    setVerticalGroup
    -0.57
    VHS
    -0.56
     للاسماء
    -0.55
    élien
    -0.54
    Berat
    -0.53
    parametrize
    -0.53
     Мексичка
    -0.53
    POSITIVE LOGITS
     orchestra
    1.16
     music
    1.05
     Orchestra
    1.03
     orchestral
    0.98
     musicians
    0.98
     Music
    0.95
     musical
    0.93
     músicos
    0.92
     composer
    0.92
     symphony
    0.91
    Activations Density 0.261%

    No Known Activations