© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 66
    Prev
    Next
    INDEX
    Explanations

    sentences expressing disappointment or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     saites
    -0.64
    SuccessListener
    -0.55
    +#+
    -0.53
    Données
    -0.52
    Халык
    -0.50
    cemia
    -0.50
    Kanpo
    -0.49
    verwijspagina
    -0.48
    Eksterne
    -0.48
     isInitialized
    -0.45
    POSITIVE LOGITS
     sad
    1.73
     :(
    1.71
    Sad
    1.60
     :-(
    1.54
     Sad
    1.53
     bummer
    1.53
     saddest
    1.51
     😔
    1.49
     :'(
    1.47
    sad
    1.46
    Activations Density 0.280%

    No Known Activations