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. 35-GEMMASCOPE-RES-16K
    6. 7334
    Prev
    Next
    INDEX
    Explanations

    names of researchers and their contributions

    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
     équilibr
    -0.52
    ſelves
    -0.51
    
    -0.47
     financière
    -0.46
    IUrlHelper
    -0.46
     prêts
    -0.46
     XNUMX
    -0.45
    ſelf
    -0.44
     laço
    -0.44
     étoient
    -0.43
    POSITIVE LOGITS
     et
    1.20
    Odkazy
    0.52
    IsMutable
    0.50
    等人
    0.50
    RectangleBorder
    0.48
     препратки
    0.46
    unpublished
    0.44
     studied
    0.44
    Referencie
    0.44
     investigated
    0.44
    Activations Density 0.585%

    No Known Activations