Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 15629
    Prev
    Next
    INDEX
    Explanations

    positive adjectives, specifically variations of the word "good."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -1.20
     itſelf
    -1.06
     Majefty
    -1.01
     fhew
    -0.99
     whoſe
    -0.94
     defire
    -0.93
     themſelves
    -0.91
     ftate
    -0.90
     Efq
    -0.90
     raiſ
    -0.90
    POSITIVE LOGITS
     good
    3.44
     Good
    3.31
    good
    3.28
    Good
    3.26
     GOOD
    3.00
    GOOD
    2.92
     buena
    2.01
     gute
    1.84
     goede
    1.80
     buenas
    1.77
    Activations Density 0.061%

    No Known Activations