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-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 82
    Prev
    Next
    INDEX
    Explanations

    relative clauses beginning with "in which" or "which".

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    instances of the word "which."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wicidata
    -0.67
    richTextPanel
    -0.63
     $_(
    -0.61
     queſta
    -0.60
    Personendaten
    -0.59
    DockStyle
    -0.57
     مشين
    -0.57
     nahilalakip
    -0.56
    fromCharCode
    -0.56
    TagNumber
    -0.56
    POSITIVE LOGITS
     where
    0.80
     waarin
    0.75
     где
    0.65
     wherein
    0.64
     où
    0.63
     Where
    0.62
    where
    0.61
     donde
    0.61
    Where
    0.60
    Où
    0.56
    Activations Density 0.487%

    No Known Activations