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. 22-GEMMASCOPE-RES-16K
    6. 10341
    Prev
    Next
    INDEX
    Explanations

    descriptions of quality and features of accommodations or facilities

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

    Follows "also", "be", "you", or "}"

    np_acts-logits-general · gemini-2.0-flash

    spacious comfortable modern equipped

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.58
    mybatisplus
    -0.50
     unexplo
    -0.50
    slow
    -0.49
    Slow
    -0.49
    NotSupported
    -0.48
    商品説明
    -0.48
    NSIndexPath
    -0.48
    protoimpl
    -0.48
    INGE
    -0.48
    POSITIVE LOGITS
     spacious
    0.91
     equipped
    0.90
     furnished
    0.87
     imma
    0.86
    modern
    0.86
     modern
    0.85
    LookAnd
    0.82
     comfortable
    0.81
     decorated
    0.79
    MODERN
    0.79
    Activations Density 0.076%

    No Known Activations