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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 2007
    Prev
    Next
    INDEX
    Explanations

    terms related to software installation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tır
    -0.58
     Tuck
    -0.53
    кро
    -0.52
    AddressBook
    -0.52
    Cite
    -0.52
     Winaray
    -0.51
     nicio
    -0.51
    ់
    -0.51
     Pind
    -0.51
    ∃
    -0.51
    POSITIVE LOGITS
    ⓧ
    1.12
     تانيه
    1.07
     يتيمه
    0.90
    حياته
    0.87
    ביוגרפיה
    0.86
     للمعارف
    0.85
    حياتها
    0.83
    
    0.81
     onCreateView
    0.81
    +#+
    0.80
    Activations Density 0.026%

    No Known Activations