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. 22-GEMMASCOPE-RES-16K
    6. 14948
    Prev
    Next
    INDEX
    Explanations

    references to animals used in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.38
    InjectMocks
    -0.31
    ComponentName
    -0.28
     Poor
    -0.28
    routeProvider
    -0.28
     生命周期
    -0.27
    ISupport
    -0.27
     chứ
    -0.25
    }}],
    -0.25
     DBNull
    -0.25
    POSITIVE LOGITS
    Diweddarwch
    0.73
     Autorizaciones
    0.70
    available
    0.67
     Autorisations
    0.66
     beschikbaar
    0.66
     available
    0.64
    Autoritní
    0.64
    availability
    0.64
     availability
    0.62
    Available
    0.59
    Activations Density 0.706%

    No Known Activations