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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 2249
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and their related contexts

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

    "its" possessive followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    possessive describing attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.64
    TagMode
    -0.58
    addPreferredGap
    -0.57
     autorytatywna
    -0.56
     Tatsache
    -0.55
    MemoryWarning
    -0.53
     questão
    -0.52
    HostException
    -0.49
    ArgumentParser
    -0.49
     Dinge
    -0.49
    POSITIVE LOGITS
     entirety
    0.97
     contents
    0.93
     existence
    0.93
    hould
    0.93
     origins
    0.92
     predecessor
    0.91
     namesake
    0.85
     inception
    0.84
     inhabitants
    0.83
    contents
    0.80
    Activations Density 0.318%

    No Known Activations