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. 22-GEMMASCOPE-RES-16K
    6. 14101
    Prev
    Next
    INDEX
    Explanations

    phrases related to familial relationships and care responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    falgar
    -0.47
     Anfänger
    -0.45
    xs
    -0.45
     habet
    -0.43
    manjaro
    -0.43
     Städten
    -0.43
    føre
    -0.42
    htä
    -0.42
     vastaan
    -0.41
    人士
    -0.40
    POSITIVE LOGITS
     mom
    2.06
     dad
    2.00
     Mom
    1.96
     Dad
    1.96
    Mom
    1.81
    Dad
    1.75
     mum
    1.75
     Mum
    1.65
     grandma
    1.61
    mom
    1.58
    Activations Density 0.566%

    No Known Activations