© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5767
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and expressions related to decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Depending on" or contingency phrases

    np_acts-logits-general · gemini-2.0-flash

    varying depending on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.76
    ьаж
    -0.75
     NSCoder
    -0.73
    :✨
    -0.72
    MemoryWarning
    -0.71
    SBATCH
    -0.70
    httphttps
    -0.69
    Hentet
    -0.69
     Numerade
    -0.67
    uxxxx
    -0.65
    POSITIVE LOGITS
     different
    0.91
     depending
    0.88
     Depending
    0.80
     whether
    0.77
    不同的
    0.76
     varying
    0.73
    Depending
    0.73
     differently
    0.71
     Different
    0.71
     unterschiedlich
    0.68
    Activations Density 0.935%

    No Known Activations