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. 2-GEMMASCOPE-RES-16K
    6. 4808
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships and in-laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ския
    -0.50
    Genius
    -0.49
     Beobach
    -0.49
     stringBy
    -0.48
     AKS
    -0.48
    itaire
    -0.47
     kao
    -0.47
    ReusableCell
    -0.47
    NonQuery
    -0.47
     Phaser
    -0.47
    POSITIVE LOGITS
     grandmother
    1.26
     grandfather
    1.19
    grandmother
    1.12
     granddaughter
    1.11
     Grandmother
    1.08
    grandfather
    1.08
     grandparents
    1.06
     Grandfather
    1.05
     grandpa
    1.05
     nephew
    1.05
    Activations Density 0.160%

    No Known Activations