© 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. 14-GEMMASCOPE-RES-16K
    11. 12650
    Prev
    Next
    INDEX
    Explanations

    references to specific colors or shades often associated with environmental or atmospheric descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    **************
    -0.93
     pinulongan
    -0.88
    ssch
    -0.84
    HHHHHHHH
    -0.81
    pement
    -0.80
    lrrr
    -0.80
     trac
    -0.78
    }))
    -0.78
    truc
    -0.78
    lcccccc
    -0.77
    POSITIVE LOGITS
    ay
    1.15
     Poy
    1.15
     Koy
    1.11
     Rays
    1.11
    AY
    1.08
     AY
    1.08
     Cray
    1.04
     Fey
    1.04
    tray
    1.03
     BAY
    1.02
    Activations Density 0.206%

    No Known Activations