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-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 12350
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and expressions of personal perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.51
     poveznice
    -0.45
    TagHelper
    -0.40
    frust
    -0.38
    偶尔
    -0.36
     frustrate
    -0.36
    
    -0.35
    getColumnIndex
    -0.34
     говорили
    -0.33
    \|_{\
    -0.32
    POSITIVE LOGITS
     reacted
    0.69
     ficou
    0.68
     react
    0.66
     quedó
    0.64
     freaked
    0.62
     reacts
    0.60
     fica
    0.59
     ficaram
    0.59
     quedado
    0.59
     immediately
    0.59
    Activations Density 0.418%

    No Known Activations