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. 25-GEMMASCOPE-RES-16K
    6. 8048
    Prev
    Next
    INDEX
    Explanations

    phrases related to problem-solving and overcoming challenges

    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
     amelyek
    -0.61
    imageshack
    -0.57
    它們
    -0.57
     quei
    -0.57
     Those
    -0.56
    queles
    -0.55
    它们
    -0.55
    Those
    -0.52
     celles
    -0.50
    those
    -0.50
    POSITIVE LOGITS
     this
    4.08
    this
    2.75
     этого
    2.00
     questo
    1.98
     này
    1.89
     questa
    1.86
     этом
    1.82
     dieses
    1.82
     هذا
    1.77
     diesem
    1.76
    Activations Density 2.669%

    No Known Activations