Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8449
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "fall" or autumn-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentValues
    -0.59
    RadioGroup
    -0.56
     dou
    -0.54
    ila
    -0.53
    兇
    -0.52
      
    -0.52
    bürger
    -0.51
    hite
    -0.51
    creativecommons
    -0.51
    🤬
    -0.51
    POSITIVE LOGITS
     fall
    4.08
    fall
    3.73
    Fall
    3.70
     Fall
    3.70
     FALL
    3.56
    FALL
    3.45
     falls
    3.08
    falls
    2.93
    falling
    2.64
     falling
    2.63
    Activations Density 0.047%

    No Known Activations