Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10332
    Prev
    Next
    INDEX
    Explanations

    references to years and annual events

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

    preceding "year"

    np_acts-logits-general · gemini-2.0-flash

    year followed by hyphen or number

    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
     يتيمه
    -0.86
    ]));
    
    -0.73
    Scénario
    -0.72
    DotNetBar
    -0.72
     mapStateToProps
    -0.72
     pinulongan
    -0.72
     LoggerFactory
    -0.69
    SpringBootTest
    -0.68
     Púb
    -0.67
    orgon
    -0.67
    POSITIVE LOGITS
     ago
    0.78
    long
    0.74
    old
    0.65
    lings
    0.65
     olds
    0.64
    round
    0.64
    lijks
    0.63
    ling
    0.62
    lijkse
    0.60
    nings
    0.60
    Activations Density 0.081%

    No Known Activations