© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10784
    Prev
    Next
    INDEX
    Explanations

    mentions of resources or resource management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ISNI
    -1.19
     AIAA
    -1.10
    IndentedString
    -1.08
     Monfieur
    -1.03
     comets
    -1.00
     Majefty
    -0.98
    FieldBuilder
    -0.97
     RouterModule
    -0.97
     roulant
    -0.96
    FXML
    -0.94
    POSITIVE LOGITS
     resource
    2.61
     resources
    2.59
     Resource
    2.19
    resource
    2.17
     Resources
    2.14
    Resource
    2.13
    Resources
    2.10
    resources
    2.06
     RESOURCE
    1.93
     ressources
    1.89
    Activations Density 0.032%

    No Known Activations