© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6250
    Prev
    Next
    INDEX
    Explanations

    references to the color pink, particularly in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CDCl
    -0.52
    ophysical
    -0.47
     contu
    -0.45
    Portrait
    -0.44
     Portrait
    -0.44
    estries
    -0.43
     flam
    -0.43
     PORTRAIT
    -0.43
    }^{+}\
    -0.42
    ADELPHIA
    -0.42
    POSITIVE LOGITS
     periodic
    0.64
     Periodic
    0.60
    ^{-
    0.59
    periodic
    0.58
    Periodic
    0.56
    MemoryWarning
    0.56
     Pink
    0.54
     pink
    0.53
     pinulongan
    0.52
    {-
    0.51
    Activations Density 0.115%

    No Known Activations