© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10627
    Prev
    Next
    INDEX
    Explanations

    references to dark themes or elements within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osoever
    -0.87
    __":
    -0.86
     propOrder
    -0.83
    ngdoc
    -0.79
    ropractic
    -0.78
    isseurs
    -0.74
    }');
    -0.73
    DeleteBehavior
    -0.73
    VolleyError
    -0.72
    mfrac
    -0.72
    POSITIVE LOGITS
     dark
    2.69
     Dark
    2.65
    Dark
    2.56
     DARK
    2.52
    dark
    2.47
    DARK
    2.31
     darkness
    1.90
     darker
    1.89
     darkest
    1.76
     Darkness
    1.69
    Activations Density 0.047%

    No Known Activations