© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80374
    Prev
    Next
    INDEX
    Explanations

    instances of specific keywords and terms related to health, medical issues, and anatomical references

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

    back pain or services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Administrativna
    -0.41
    rouvez
    -0.34
    SneakyThrows
    -0.33
     chì
    -0.33
    tangentMode
    -0.32
     melt
    -0.32
    żesz
    -0.32
     FishBase
    -0.31
     Equip
    -0.31
    ent
    -0.31
    POSITIVE LOGITS
    rungsseite
    0.56
     TestBed
    0.54
    IndentedString
    0.52
    ValueStyle
    0.52
     &___
    0.51
    principalTable
    0.51
    fjspx
    0.51
     noDo
    0.50
     Савезне
    0.49
    WriteTagHelper
    0.49
    Activations Density 0.204%

    No Known Activations