© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4618
    Prev
    Next
    INDEX
    Explanations

    elements related to structured arguments or reasoning, particularly those indicating sequential points or lists

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

    Ordinal numbers (first, second) and related terms

    np_acts-logits-general · gemini-2.0-flash

    first, second, third

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.42
     magasiner
    -0.41
    __*/
    -0.40
    AutoresizingMask
    -0.40
     čierna
    -0.40
     Numerade
    -0.40
    mitives
    -0.39
     onBackPressed
    -0.37
    Filmographie
    -0.37
    égories
    -0.36
    POSITIVE LOGITS
     secondly
    2.28
    Secondly
    2.13
     Secondly
    2.08
     second
    1.98
    second
    1.80
    Second
    1.62
     Second
    1.58
    其次
    1.52
     SECOND
    1.51
     segundo
    1.39
    Activations Density 0.833%

    No Known Activations