© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 13425
    Prev
    Next
    INDEX
    Explanations

    phrases related to experimentation and trial-and-error processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uxxxx
    -0.73
    SBATCH
    -0.67
    makeText
    -0.61
    BagConstraints
    -0.60
    はじめに
    -0.60
    inflate
    -0.57
    úp
    -0.57
    httphttps
    -0.55
    JvmStatic
    -0.54
     CreateTagHelper
    -0.54
    POSITIVE LOGITS
     experimentation
    1.50
     experimenting
    1.46
     trial
    1.36
     experiment
    1.32
     experimented
    1.28
     Experiment
    1.28
     experiments
    1.27
    Experiment
    1.15
    trial
    1.13
     exploration
    1.12
    Activations Density 0.609%

    No Known Activations