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. 6924
    Prev
    Next
    INDEX
    Explanations

    emotional expressions and personal reflections regarding motherhood and the challenges of parenting

    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
    twimg
    -0.54
    yntaxException
    -0.50
    BibitemShut
    -0.49
    oliver
    -0.48
    󠁿
    -0.48
    escens
    -0.47
    setVerticalGroup
    -0.47
    Ӕ
    -0.46
    Према
    -0.45
     Alt
    -0.45
    POSITIVE LOGITS
     Somebody
    0.60
    Somebody
    0.59
     somebody
    0.56
    Nobody
    0.54
     Nobody
    0.52
    somebody
    0.51
     nobody
    0.49
    nobody
    0.48
    Everybody
    0.45
     Everybody
    0.42
    Activations Density 0.144%

    No Known Activations