© 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. 18-GEMMASCOPE-RES-16K
    11. 950
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and procedural outcomes

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

    flaws or failures

    np_acts-logits-general · gemini-2.0-flash

    shortcomings or failures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.79
    :✨
    -0.68
    сылкі
    -0.59
    NewUrlParser
    -0.55
     unknownFields
    -0.53
    RuleContext
    -0.52
    Diweddarwch
    -0.51
     disambiguazione
    -0.50
     okuyayım
    -0.50
    ännande
    -0.49
    POSITIVE LOGITS
     deficiencies
    1.74
     deficient
    1.64
     shortcomings
    1.62
     lacking
    1.56
     failings
    1.54
     deficiency
    1.53
     Defic
    1.46
     shortfall
    1.40
     lacked
    1.39
     failures
    1.37
    Activations Density 0.402%

    No Known Activations