© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 7104
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and function definitions in code, particularly focusing on file handling and data manipulation

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

    Code related to offsets, lines, and positions

    np_acts-logits-general · gemini-2.0-flash

    offsets and positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    NewGuid
    -0.47
     isEqualToString
    -0.47
    contentValues
    -0.46
     Them
    -0.44
     tute
    -0.44
    edly
    -0.43
    makeText
    -0.43
    زار
    -0.41
     newName
    -0.41
     FormBuilder
    -0.40
    POSITIVE LOGITS
     offset
    1.08
    offset
    1.05
     position
    0.97
     Offset
    0.95
    Offset
    0.94
     starting
    0.93
     location
    0.92
     start
    0.90
     offsets
    0.88
     positions
    0.86
    Activations Density 0.802%

    No Known Activations