© 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. 2-GEMMASCOPE-RES-16K
    11. 3948
    Prev
    Next
    INDEX
    Explanations

    terms related to radial geometry or structure in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    ppuden
    -0.44
     AttributeSet
    -0.43
    もしろ
    -0.42
     disambiguazione
    -0.40
     cata
    -0.39
     compen
    -0.39
     lenker
    -0.39
    ůměr
    -0.38
    TokenNameDOT
    -0.38
    tanleria
    -0.37
    POSITIVE LOGITS
    xx
    0.59
    oy
    0.56
    されていて
    0.56
    される
    0.55
    された
    0.54
     radial
    0.54
    されている
    0.53
    され
    0.53
    されており
    0.52
    されて
    0.51
    Activations Density 0.661%

    No Known Activations