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-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16156
    Prev
    Next
    INDEX
    Explanations

    expressions of comparison and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Comes before comparative adjectives

    np_acts-logits-general · gemini-2.0-flash

    comparative or superlative evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    不一樣
    -0.49
     considerably
    -0.47
    very
    -0.44
    Referencias
    -0.41
     veldig
    -0.41
    不一样
    -0.40
    ędziesz
    -0.39
     considérable
    -0.37
    sanity
    -0.37
    digit
    -0.36
    POSITIVE LOGITS
     better
    1.04
    better
    0.88
    Better
    0.79
     besser
    0.76
     Better
    0.74
     beter
    0.74
     BETTER
    0.72
     mejor
    0.71
     melhor
    0.69
     betere
    0.67
    Activations Density 0.097%

    No Known Activations