© 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. 2-GEMMASCOPE-RES-16K
    6. 6112
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "An" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \{\\
    -0.96
     MainAxisSize
    -0.90
     StatefulWidget
    -0.89
    LookAnd
    -0.83
    Sucesor
    -0.81
     tartalomajánló
    -0.80
    mybatisplus
    -0.78
    الحياه
    -0.76
     виправивши
    -0.76
    URLException
    -0.76
    POSITIVE LOGITS
     An
    2.62
    An
    2.41
     AN
    1.20
    an
    0.97
     Ан
    0.90
    安
    0.86
    AN
    0.83
    The
    0.83
     The
    0.77
    Ан
    0.74
    Activations Density 0.070%

    No Known Activations