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. 4-GEMMASCOPE-RES-16K
    6. 11149
    Prev
    Next
    INDEX
    Explanations

    keywords and concepts related to programming constructs and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichord
    -0.90
    CloseOperation
    -0.87
    windowFixed
    -0.86
     Roskov
    -0.80
    NameInMap
    -0.80
    存于互联网档案馆
    -0.77
     Савезне
    -0.77
    EDEFAULT
    -0.75
    Viited
    -0.74
     AppCompatTheme
    -0.74
    POSITIVE LOGITS
     er
    0.40
    liti
    0.39
    GetEnumerator
    0.39
    </code>
    0.37
    ato
    0.36
    警
    0.35
    con
    0.33
    Trama
    0.33
    atic
    0.33
    ster
    0.33
    Activations Density 1.071%

    No Known Activations