© 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. 8212
    Prev
    Next
    INDEX
    Explanations

    research studies that investigate various scientific concepts or phenomena

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

    followed by "the" related to investigation

    np_acts-logits-general · gemini-2.0-flash

    research study investigation

    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
     disambiguazione
    -0.65
    хьтан
    -0.51
     виправивши
    -0.51
    istoitu
    -0.50
    章节错误
    -0.48
    DialogContent
    -0.47
     Synopsis
    -0.47
    ceğine
    -0.46
    EndContext
    -0.44
    TRIBUN
    -0.43
    POSITIVE LOGITS
     how
    0.81
     bagaimana
    0.73
     defaultstate
    0.71
     cómo
    0.68
     effects
    0.59
     איך
    0.57
     relationships
    0.56
     Auswirkungen
    0.56
     interactions
    0.55
    holdet
    0.55
    Activations Density 1.344%

    No Known Activations