Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12503
    Prev
    Next
    INDEX
    Explanations

    information related to marriage and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.92
    ſelf
    -0.85
    AndEndTag
    -0.84
    ſelves
    -0.83
     betweenstory
    -0.82
    нгред
    -0.79
     myſelf
    -0.78
    Personendaten
    -0.76
     Houſe
    -0.76
    出版年
    -0.74
    POSITIVE LOGITS
    ↵↵
    0.29
     or
    0.28
     corner
    0.28
     Robertson
    0.28
     and
    0.28
    (
    0.28
     ogen
    0.27
     GoogleFonts
    0.27
     voces
    0.27
     Raj
    0.27
    Activations Density 0.194%

    No Known Activations