© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 7897
    Prev
    Next
    INDEX
    Explanations

    reports or statements regarding new knowledge or research findings

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

    "This is the first" or "This work reports the first"

    np_acts-logits-general · gemini-2.0-flash

    first reportMarking this is the first

    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
    sequelize
    -0.51
     ContentValues
    -0.49
    /*
    -0.49
    ாய
    -0.49
    SpringBootTest
    -0.48
    ?>
    
    -0.48
    TableAdapter
    -0.47
     %>%
    -0.47
    UnusedPrivate
    -0.47
    rror
    -0.46
    POSITIVE LOGITS
     marking
    0.97
     marks
    0.94
    marking
    0.80
     MARKS
    0.77
    这也是
    0.77
     marked
    0.75
    __*/
    0.75
     Marking
    0.74
     ujedno
    0.73
     markiert
    0.71
    Activations Density 0.132%

    No Known Activations