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. 19-GEMMASCOPE-RES-16K
    6. 11831
    Prev
    Next
    INDEX
    Explanations

    references to "mother" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MIDDLEWARE
    -0.66
     linkovi
    -0.63
    ReusableCell
    -0.61
     VIAF
    -0.60
     nahilalakip
    -0.60
     ExecuteAsync
    -0.58
    期刊论文
    -0.57
     iParam
    -0.55
    setContentView
    -0.55
    ValueGeneration
    -0.54
    POSITIVE LOGITS
    Mothers
    0.86
     Mother
    0.78
     MOTHER
    0.78
     Mothers
    0.76
    Mother
    0.76
    MOTHER
    0.75
     mothers
    0.69
    fucker
    0.68
    fucking
    0.67
     mother
    0.65
    Activations Density 0.031%

    No Known Activations