Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 92306
    Prev
    Next
    INDEX
    Explanations

    prepositions and auxiliary verbs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.90
     Normdatei
    -0.81
     esternos
    -0.79
     تضيفلها
    -0.77
    帖最后由
    -0.74
     noqa
    -0.74
    Tembelea
    -0.72
     дописавши
    -0.71
    uxxxx
    -0.71
    OGND
    -0.70
    POSITIVE LOGITS
     also
    0.49
     especially
    0.49
     particularly
    0.47
     Verhältnisse
    0.40
     ihtiyac
    0.40
     Entstehung
    0.40
    With
    0.40
     bijzonder
    0.39
     Tatsache
    0.39
     različ
    0.38
    Activations Density 0.070%

    No Known Activations