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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 13992
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the color black or identities associated with blackness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.24
    MessageTagHelper
    -1.02
    __":
    
    -1.02
    =$?
    -0.99
    RenderAtEndOf
    -0.98
    Personensuche
    -0.96
    })*/
    -0.95
     --}}
    -0.94
     Roskov
    -0.94
     للاسماء
    -0.94
    POSITIVE LOGITS
     Black
    1.67
    Black
    1.65
     BLACK
    1.59
    black
    1.55
     black
    1.51
    BLACK
    1.50
     blacks
    1.24
     Blackwell
    1.22
     Blacks
    1.19
     Schwar
    1.15
    Activations Density 0.044%

    No Known Activations