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. 21-GEMMASCOPE-RES-16K
    6. 7140
    Prev
    Next
    INDEX
    Explanations

    phrases related to eligibility and qualifications, particularly in legal and financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.43
     diretta
    -0.43
    WebElementEntity
    -0.41
     cocinar
    -0.40
     creadores
    -0.40
    ⓧ
    -0.40
    tonode
    -0.39
     Infórmanos
    -0.38
     antemano
    -0.38
     montanha
    -0.38
    POSITIVE LOGITS
     successful
    0.54
     succes
    0.51
     suc
    0.51
     truly
    0.49
     effective
    0.49
     successfully
    0.49
     survi
    0.48
     success
    0.48
     isSuccess
    0.47
     survival
    0.47
    Activations Density 0.726%

    No Known Activations