© 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. 8-GEMMASCOPE-RES-16K
    11. 10574
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate direction or progression towards a goal or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Calvo
    -0.84
     foglal
    -0.76
     poffe
    -0.70
     riuscito
    -0.69
     fatica
    -0.69
     vandens
    -0.67
    5
    -0.67
     assoluto
    -0.67
     grunn
    -0.66
    물
    -0.66
    POSITIVE LOGITS
    toward
    1.91
    towards
    1.88
     toward
    1.86
     Towards
    1.84
     Toward
    1.83
    Towards
    1.79
     towards
    1.76
    Toward
    1.72
     hacia
    1.30
     TOW
    1.20
    Activations Density 0.058%

    No Known Activations