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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 11553
    Prev
    Next
    INDEX
    Explanations

    code snippets related to API requests and handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RefreshLayout
    -0.50
    crollView
    -0.44
    SerializedSize
    -0.42
     HttpHeaders
    -0.42
    URLException
    -0.41
     schedules
    -0.41
     isInitialized
    -0.40
    ManagedBean
    -0.40
     FontWeight
    -0.40
    QtCore
    -0.40
    POSITIVE LOGITS
     Simple
    0.56
    出版年
    0.56
     implementa
    0.55
     Default
    0.54
     implementing
    0.54
    Default
    0.51
     implemented
    0.51
     simplistic
    0.50
    implemented
    0.49
    impl
    0.49
    Activations Density 0.601%

    No Known Activations