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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 146
    Prev
    Next
    INDEX
    Explanations

    references to databases and object-relational mapping components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.79
    IndentedString
    -0.69
     Administrativna
    -0.66
    parsedMessage
    -0.63
     فريبيس
    -0.62
     المعيارى
    -0.61
    EnumMember
    -0.59
     betweenstory
    -0.59
     disambiguazione
    -0.56
    ScreenState
    -0.56
    POSITIVE LOGITS
    userDao
    0.56
    UserRepository
    0.55
     UserRepository
    0.47
     userDao
    0.45
    Repositories
    0.45
    userRepository
    0.45
    UserDao
    0.44
     UserDao
    0.44
     JpaRepository
    0.44
     userRepository
    0.42
    Activations Density 0.046%

    No Known Activations