© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 82171
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate low-cost or inexpensive items or services

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

    low cost and comparisons

    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
     Rollins
    -0.53
    SSI
    -0.52
    endwhile
    -0.52
     present
    -0.52
    umask
    -0.52
    FormState
    -0.51
    RSM
    -0.51
    IntentFilter
    -0.51
    addEventListener
    -0.50
    ViewSet
    -0.49
    POSITIVE LOGITS
    Cheap
    1.13
     cheap
    1.05
     Cheap
    1.03
    cheap
    0.98
     cheapest
    0.84
     barato
    0.83
     cheaper
    0.82
     Cheaper
    0.79
     деше
    0.74
     Cheapest
    0.73
    Activations Density 0.005%

    No Known Activations