© 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. 20-GEMMASCOPE-RES-16K
    11. 8568
    Prev
    Next
    INDEX
    Explanations

    numerical values and their varying magnitudes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iſen
    -1.39
    majánló
    -1.26
     ſind
    -1.26
     queſta
    -1.23
     فريبيس
    -1.18
    ロウィン
    -1.18
     témoig
    -1.17
     ſein
    -1.16
     geſch
    -1.16
     beſch
    -1.16
    POSITIVE LOGITS
    0
    0.69
    s
    0.68
    \
    0.64
    [toxicity=0]
    0.59
    {
    0.59
    ,
    0.56
    1
    0.56
    -
    0.56
      
    0.56
     
    0.56
    Activations Density 0.047%

    No Known Activations