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. 8525
    Prev
    Next
    INDEX
    Explanations

    references to specific places and organizations

    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-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
    NewUrlParser
    -0.41
     tuvimos
    -0.40
     doInBackground
    -0.40
     vœ
    -0.39
    PYX
    -0.38
    -------------</
    -0.38
     sorpresas
    -0.38
    antwoorden
    -0.38
    esistenza
    -0.37
    Reprodução
    -0.37
    POSITIVE LOGITS
    Portale
    0.58
     the
    0.56
    󠁢
    0.53
     Référence
    0.52
     Ghana
    0.51
     Britain
    0.47
     newly
    0.46
     America
    0.44
     Ireland
    0.43
    __(/*!
    0.43
    Activations Density 0.329%

    No Known Activations