© 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. 21-GEMMASCOPE-RES-16K
    6. 15478
    Prev
    Next
    INDEX
    Explanations

    financial figures and statistics related to impacts from natural disasters, specifically wildfires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     twenty
    -0.98
     Whilst
    -0.98
    Whilst
    -0.94
     eighteen
    -0.92
     seventeen
    -0.92
     twelve
    -0.90
     thirty
    -0.89
     thirteen
    -0.87
     sixty
    -0.87
     fourteen
    -0.86
    POSITIVE LOGITS
    ?''
    0.72
    ,''
    0.66
    . 
    0.64
    ReusableCell
    0.64
    ‴
    0.60
    routeProvider
    0.60
    Portale
    0.59
     doubtnut
    0.59
     ▶
    0.59
    InputBorder
    0.58
    Activations Density 0.186%

    No Known Activations