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. 3-GEMMASCOPE-RES-16K
    6. 6214
    Prev
    Next
    INDEX
    Explanations

    references to mothers and maternal figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Danilo
    -0.77
    ](#
    -0.75
    ardust
    -0.69
    SuppressMessage
    -0.69
     Arif
    -0.66
    capaian
    -0.66
    viato
    -0.65
    ==",
    -0.64
     Pickles
    -0.64
     Arundel
    -0.63
    POSITIVE LOGITS
     mother
    2.60
     Mother
    2.52
     mothers
    2.39
    Mother
    2.38
     MOTHER
    2.36
    mother
    2.32
     Mothers
    2.25
    MOTHER
    2.17
    Mothers
    2.14
     madre
    1.89
    Activations Density 0.036%

    No Known Activations