© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 13078
    Prev
    Next
    INDEX
    Explanations

    references to the term "white" in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __":
    -0.94
     bezeichneter
    -0.84
    rrggbb
    -0.82
    __':
    -0.82
     autorytatywna
    -0.82
    NameInMap
    -0.80
    __":
    -0.78
    يكب
    -0.75
    MessageTagHelper
    -0.75
    WriteTagHelper
    -0.75
    POSITIVE LOGITS
     White
    1.31
    White
    1.20
     white
    1.19
     WHITE
    1.15
    white
    1.14
    WHITE
    1.14
     Whites
    1.09
    白
    1.01
    Whites
    0.99
     blanca
    0.96
    Activations Density 0.140%

    No Known Activations