© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7455
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "ideal" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nyky
    -0.58
     tunggal
    -0.54
    /*
    -0.54
     anaknya
    -0.47
     Flucht
    -0.47
     Furcht
    -0.47
     setempat
    -0.46
     tästä
    -0.46
     expertos
    -0.46
     financiero
    -0.46
    POSITIVE LOGITS
     ideal
    1.36
    ideal
    1.14
     Ideal
    1.13
     ideally
    1.11
    Ideal
    1.02
     IDEAL
    0.97
     Ideally
    0.96
    理想
    0.94
     ideale
    0.90
     ide
    0.88
    Activations Density 0.171%

    No Known Activations