Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 1119
    Prev
    Next
    INDEX
    Explanations

    sections discussing advantages and disadvantages, as well as terms related to sensitivity and facilitators in a scientific or technical context

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

    benefits, advantages, or greater outcomes

    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
     protoimpl
    -0.78
     ddelwed
    -0.77
     للمعارف
    -0.73
     témoig
    -0.72
     تضيفلها
    -0.71
     ſei
    -0.70
    errHandler
    -0.69
     kasarigan
    -0.69
    ロウィン
    -0.69
    ſammen
    -0.68
    POSITIVE LOGITS
     avantages
    0.38
     vôtre
    0.35
     vantaggi
    0.34
     debería
    0.32
    Avantages
    0.32
     Benefits
    0.32
    Advantages
    0.32
     advantages
    0.32
     vs
    0.32
    Benefits
    0.31
    Activations Density 0.001%

    No Known Activations