© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 12532
    Prev
    Next
    INDEX
    Explanations

    instances of failure or attempted actions that did not succeed, particularly in a political or historical context

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

    failing or failure

    np_acts-logits-general · gemini-2.0-flash

    success or failure outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    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
    -0.65
    jooq
    -0.60
    BoxShadow
    -0.59
    zzleHttp
    -0.57
     ExecuteAsync
    -0.56
    PerformLayout
    -0.56
    exitRule
    -0.54
    GoogleMap
    -0.53
    AndEndTag
    -0.53
    IMPORTED
    -0.53
    POSITIVE LOGITS
     failure
    3.02
     failed
    2.92
     fail
    2.73
     Failure
    2.60
     failures
    2.59
    failure
    2.54
     fails
    2.54
     failing
    2.51
    failed
    2.44
    Failure
    2.41
    Activations Density 0.734%

    No Known Activations