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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 113722
    Prev
    Next
    INDEX
    Explanations

    language and concepts surrounding accountability and modernization in organizational contexts

    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
     dépasse
    -0.38
    </b>
    -0.37
     nevertheless
    -0.37
    .”
    -0.35
     /\.(
    -0.35
     nonetheless
    -0.34
    AFFIRMED
    -0.34
     meliputi
    -0.34
    </h4>
    -0.34
     muualla
    -0.33
    POSITIVE LOGITS
    Personendaten
    0.72
    saraba
    0.59
     оригіналу
    0.58
    CppMethod
    0.55
    تقاوى
    0.53
    ngdoc
    0.52
    UnknownFieldSet
    0.52
     $_"
    0.52
     cref
    0.52
     '{@
    0.51
    Activations Density 0.027%

    No Known Activations