© 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. 15271
    Prev
    Next
    INDEX
    Explanations

    instances of failure or inadequacy

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

    preceding "to" indicating failure

    np_acts-logits-general · gemini-2.0-flash

    failure to act or succeed

    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
    AndEndTag
    -0.78
    ">//
    -0.73
     autorytatywna
    -0.70
    utnik
    -0.69
    ="@+
    -0.63
    WireFormatLite
    -0.62
    SqlClient
    -0.61
    KommentareTeilen
    -0.58
    IntoConstraints
    -0.57
     AssemblyCompany
    -0.56
    POSITIVE LOGITS
     miserably
    1.13
     Fail
    1.08
     fail
    1.03
     fails
    0.96
     failures
    0.95
     Failure
    0.94
     failure
    0.93
     Fails
    0.90
     Failures
    0.89
     FAIL
    0.89
    Activations Density 0.086%

    No Known Activations