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. 14-GEMMASCOPE-RES-16K
    6. 10674
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to command line syntax and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     xs
    -0.70
     hausse
    -0.69
     Hef
    -0.67
     cheeks
    -0.64
     marginal
    -0.62
     Miser
    -0.59
     ears
    -0.59
    iterate
    -0.59
    СЯ
    -0.59
    
    -0.58
    POSITIVE LOGITS
     commands
    1.57
     Command
    1.46
    commands
    1.45
     command
    1.44
     Commands
    1.44
    COMMAND
    1.38
    Command
    1.36
     COMMAND
    1.35
    command
    1.33
     SqlCommand
    1.31
    Activations Density 0.103%

    No Known Activations