© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3014
    Prev
    Next
    INDEX
    Explanations

    references to historical or academic contexts, particularly around regulations and organizational structures

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

    a later time

    np_acts-logits-general · gemini-2.0-flash

    later temporal events

    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
    
    -0.70
     Italijanski
    -0.50
     Италијани
    -0.48
    abetes
    -0.47
     morrow
    -0.43
    batore
    -0.43
    第一天
    -0.42
    oa̍t
    -0.41
    oldValue
    -0.40
    física
    -0.40
    POSITIVE LOGITS
     later
    2.63
    later
    2.16
    Later
    2.09
     Later
    2.02
     später
    1.98
     subsequent
    1.93
     senere
    1.82
     späteren
    1.81
     pozdě
    1.76
     subsequently
    1.75
    Activations Density 1.103%

    No Known Activations