© 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. 28-GEMMASCOPE-RES-16K
    11. 8228
    Prev
    Next
    INDEX
    Explanations

    references to miscellaneous or additional items and concepts that are not explicitly detailed

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

    Abbreviations and Latin abbreviations

    np_acts-logits-general · gemini-2.0-flash

    abbreviations followed by punctuation or specific words

    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
     Monfieur
    -0.57
     faſt
    -0.57
     ]
    -0.56
     Majefty
    -0.55
     canst
    -0.55
    UserScript
    -0.55
     Houſe
    -0.55
     Anſ
    -0.54
     ſich
    -0.54
    awtextra
    -0.54
    POSITIVE LOGITS
    etera
    0.66
     quedado
    0.39
     etc
    0.38
     orgánica
    0.38
    .,
    0.38
    ownic
    0.37
     vroe
    0.36
     galore
    0.35
     eigene
    0.35
    方面的
    0.35
    Activations Density 0.186%

    No Known Activations