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. 7077
    Prev
    Next
    INDEX
    Explanations

    sentiments related to emotional struggle, personal growth, and relationships

    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
    iestety
    -0.48
     Apalagi
    -0.45
    felizmente
    -0.44
     kijang
    -0.43
     Nación
    -0.43
     ffilm
    -0.42
    weder
    -0.42
     cuenca
    -0.42
     Simplemente
    -0.41
     Nieren
    -0.41
    POSITIVE LOGITS
    あえて
    0.50
    enterOuterAlt
    0.46
    findpost
    0.45
     challenge
    0.43
     Photocase
    0.42
     purposely
    0.41
    Datuak
    0.41
     exciting
    0.39
    apropri
    0.39
    دانشنامهٔ
    0.38
    Activations Density 0.407%

    No Known Activations