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. 15461
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

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

    Follows a form of the verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    past tense constructions

    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
    قایناقلار
    -0.53
     resourceCulture
    -0.52
    rungsseite
    -0.51
    NameInMap
    -0.49
    ResumeLayout
    -0.46
     nakalista
    -0.45
    Autoritní
    -0.44
     autorytatywna
    -0.43
     endblock
    -0.42
     Dens
    -0.40
    POSITIVE LOGITS
     previously
    0.82
     formerly
    0.78
    previously
    0.77
     recently
    0.74
     vroeger
    0.73
     Previously
    0.71
     précédemment
    0.70
     autrefois
    0.69
    recently
    0.69
    Previously
    0.69
    Activations Density 0.412%

    No Known Activations