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. 9-GEMMASCOPE-RES-16K
    6. 15240
    Prev
    Next
    INDEX
    Explanations

    phrases comparing quantities or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gass
    -0.84
    bufio
    -0.69
    Busch
    -0.66
     Koss
    -0.65
    Malawi
    -0.65
    ②
    -0.64
     FTIR
    -0.63
    ẻo
    -0.63
     Jäger
    -0.63
     koper
    -0.62
    POSITIVE LOGITS
     THAN
    1.14
     than
    0.98
     Than
    0.97
    Than
    0.89
     dozen
    0.89
    CloseOperation
    0.86
    THAN
    0.83
    OrEqual
    0.83
    GreaterThan
    0.82
     kuin
    0.81
    Activations Density 0.079%

    No Known Activations