© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 316
    Prev
    Next
    INDEX
    Explanations

    elements related to people sharing personal stories and insights about their lives and achievements

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

    Begins a block/test within code

    np_acts-logits-general · gemini-2.0-flash

    tests using 'it'

    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
    “
    -1.01
    ["
    -0.98
    {"
    -0.94
     (“
    -0.91
     "/"
    -0.89
     ("
    -0.87
     “
    -0.87
    ]["
    -0.87
    ("
    -0.86
     "/")
    -0.85
    POSITIVE LOGITS
     '
    2.37
     ‘
    2.35
    『
    1.84
    、『
    1.68
     (‘
    1.55
    。『
    1.53
    ='
    1.49
     ‚
    1.47
     ('
    1.44
     '(
    1.42
    Activations Density 0.380%

    No Known Activations