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. 20-GEMMASCOPE-RES-16K
    6. 1173
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement and enthusiasm about new products or developments

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

    Followed by common English prepositions

    np_acts-logits-general · gemini-2.0-flash

    real opportunity or wild horse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     հղումներ
    -0.59
     surla
    -0.58
    Спасылкі
    -0.58
     CreateTagHelper
    -0.55
    formik
    -0.54
     disambiguazione
    -0.52
    Nuorodos
    -0.52
     henvisninger
    -0.51
    rungsseite
    -0.49
     linkovi
    -0.49
    POSITIVE LOGITS
    发表于
    0.38
    providedIn
    0.38
    "`
    0.37
     pleaſure
    0.36
    ‗
    0.35
     our
    0.34
    是我们
    0.33
     vår
    0.32
    enterOuterAlt
    0.32
     doInBackground
    0.32
    Activations Density 0.060%

    No Known Activations