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. 16-GEMMASCOPE-RES-16K
    6. 14973
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ownership and personal responsibility

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

    Possessive pronouns or nouns

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and ownership

    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
    DockStyle
    -0.60
    offs
    -0.53
    AIRE
    -0.49
    ViewFeatures
    -0.49
    رد
    -0.47
     通販
    -0.46
    EditorBrowsable
    -0.46
    Források
    -0.45
    stringstream
    -0.44
    vábbi
    -0.44
    POSITIVE LOGITS
    BagLayout
    0.74
     own
    0.70
     responsibility
    0.64
     prerogative
    0.64
     fault
    0.61
     bedo
    0.58
     ultimate
    0.56
     preferred
    0.56
     persön
    0.56
     personal
    0.53
    Activations Density 0.134%

    No Known Activations