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. 6285
    Prev
    Next
    INDEX
    Explanations

    mentions of familial relationships and caregiving responsibilities

    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
     Buna
    -0.32
     soft
    -0.30
     ग्राहक
    -0.29
    PositiveButton
    -0.28
    исправ
    -0.28
    nloa
    -0.28
     Soft
    -0.27
    блиоте
    -0.27
     function
    -0.27
     shot
    -0.27
    POSITIVE LOGITS
    WriteTagHelper
    0.86
    AddTagHelper
    0.86
     CreateTagHelper
    0.73
    دانشنامهٔ
    0.66
    RegressionTest
    0.65
    GOTREF
    0.64
    SharedCtor
    0.63
    $_['
    0.63
    +#+#
    0.60
     dAtA
    0.60
    Activations Density 0.256%

    No Known Activations