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. 1-GEMMASCOPE-RES-16K
    6. 10209
    Prev
    Next
    INDEX
    Explanations

    references to repetitive daily activities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.84
    脚注の使い方
    -0.77
     purpoſe
    -0.77
    ształ
    -0.74
    InteropServices
    -0.72
     cauſe
    -0.72
    spyOn
    -0.71
    Personensuche
    -0.70
     doInBackground
    -0.70
     Efq
    -0.70
    POSITIVE LOGITS
     verbal
    0.67
     verbally
    0.64
    verbal
    0.57
    Verbal
    0.53
     препратки
    0.52
     Verbal
    0.49
     מוד
    0.47
    NOC
    0.47
    tawa
    0.47
    RemoteException
    0.46
    Activations Density 0.112%

    No Known Activations