© 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. 1-GEMMASCOPE-RES-16K
    6. 4985
    Prev
    Next
    INDEX
    Explanations

    terms related to geographic orientation, specifically the reference to northern and southern regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recognising
    -0.55
    OURI
    -0.54
     culti
    -0.52
    asius
    -0.51
     platform
    -0.50
     platforms
    -0.50
    hbase
    -0.49
    izi
    -0.49
    mrc
    -0.49
     MDC
    -0.48
    POSITIVE LOGITS
     south
    1.00
     &___
    0.90
     north
    0.79
     Signalez
    0.77
     northern
    0.76
    TypedDataSet
    0.70
    northern
    0.69
    RegressionTest
    0.69
    enterOuterAlt
    0.68
    تفصیلات
    0.68
    Activations Density 0.100%

    No Known Activations