Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12249
    Prev
    Next
    INDEX
    Explanations

    qualities related to emotional depth and personal connections in relationships

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

    preceding nouns or descriptions

    np_acts-logits-general · gemini-2.0-flash

    owning subsidiarylimited governmentsoulful journeyevocative journeyTimeline ofPart VI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.93
     nahilalakip
    -0.82
    
    -0.79
    Personendaten
    -0.74
    :+:
    -0.71
    AndEndTag
    -0.69
    tvguidetime
    -0.69
    didSet
    -0.69
     विश्वसनीयता
    -0.69
    SequentialGroup
    -0.68
    POSITIVE LOGITS
    abstractmethod
    0.59
     looking
    0.52
    样子
    0.51
    ropriate
    0.49
    OrEmpty
    0.49
    TargetException
    0.47
    وى
    0.47
    ❹
    0.47
    looking
    0.46
     Yol
    0.45
    Activations Density 0.166%

    No Known Activations