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. 5-GEMMASCOPE-RES-16K
    6. 7128
    Prev
    Next
    INDEX
    Explanations

    instances of the word "further" and its variations, indicating a focus on ongoing research and investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setContentType
    -0.74
    DOCTYPE
    -0.74
     Sanz
    -0.71
    riott
    -0.70
     Koe
    -0.70
     Colman
    -0.70
    kranz
    -0.70
     Epide
    -0.68
    źć
    -0.68
     Consultez
    -0.68
    POSITIVE LOGITS
     further
    2.26
    further
    2.15
    Further
    2.04
     Further
    2.02
     FURTHER
    1.92
    FURTHER
    1.89
    urther
    1.88
    进一步
    1.54
     farther
    1.33
     ulteriori
    1.27
    Activations Density 0.101%

    No Known Activations