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. 3-GEMMASCOPE-RES-16K
    6. 10297
    Prev
    Next
    INDEX
    Explanations

    complex mathematical or coding symbols, particularly related to operations or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rhestr
    -0.70
     MessageBoxIcon
    -0.62
     GRAN
    -0.59
    arschu
    -0.57
    Dés
    -0.56
    Ngoài
    -0.56
     tabPage
    -0.56
     berkom
    -0.55
    Pranala
    -0.54
    ėk
    -0.54
    POSITIVE LOGITS
     &
    1.18
    </th>
    1.06
     &=&
    1.03
    <td>
    0.98
    &=&
    0.86
    </td>
    0.85
    <th>
    0.79
    ]-->
    0.79
    ])]
    0.78
    enderror
    0.75
    Activations Density 0.041%

    No Known Activations