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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 683
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and claims

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

    Formality in emails or letters

    np_acts-logits-general · gemini-2.0-flash

    attached and sent information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.62
    Съ
    -0.48
    Personendaten
    -0.46
     useAppContext
    -0.44
    出版年
    -0.44
    sena
    -0.44
    banners
    -0.43
     betweenstory
    -0.43
    sne
    -0.42
    嘿
    -0.42
    POSITIVE LOGITS
    ISupport
    0.49
     colleague
    0.43
     transfieras
    0.40
     GenerationType
    0.39
    AutoScale
    0.38
    息
    0.37
    findpost
    0.37
    CppMethod
    0.37
    omitempty
    0.36
     neque
    0.36
    Activations Density 0.511%

    No Known Activations