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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 2715
    Prev
    Next
    INDEX
    Explanations

    emotional and relational values associated with people's preferences and social perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    protoc
    -0.59
     dermed
    -0.49
     provisional
    -0.47
    عث
    -0.47
     spørgsmål
    -0.46
    BindingResult
    -0.46
    ServletException
    -0.45
    apis
    -0.45
     doInBackground
    -0.45
     maand
    -0.45
    POSITIVE LOGITS
    +#+#
    0.76
     preferring
    0.73
     OFDb
    0.69
     dislike
    0.68
     aversion
    0.67
     предпочита
    0.67
     prefers
    0.66
     abhor
    0.66
     esche
    0.65
     hates
    0.64
    Activations Density 0.422%

    No Known Activations