© 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. 16-GEMMASCOPE-RES-16K
    6. 14575
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to law enforcement and legal processes

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

    Follows conjunctions/punctuation with a pronoun

    np_acts-logits-general · gemini-2.0-flash

    continuing despite contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    defer
    -0.49
    ']),
    -0.48
    OrBuilder
    -0.47
    かね
    -0.46
    من
    -0.46
    ()?;
    -0.45
    Merkmale
    -0.44
    menu
    -0.44
    reiche
    -0.43
    "}},
    -0.43
    POSITIVE LOGITS
     still
    1.92
    still
    1.89
    Still
    1.81
     yet
    1.79
     trotzdem
    1.75
     STILL
    1.71
     Still
    1.69
    それでも
    1.69
     nevertheless
    1.66
     dennoch
    1.62
    Activations Density 0.352%

    No Known Activations