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. 8-GEMMASCOPE-RES-16K
    6. 5989
    Prev
    Next
    INDEX
    Explanations

    elements indicating code structure or programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -0.69
    зец
    -0.67
     _("
    -0.61
     inyección
    -0.59
    ^(@)
    -0.58
    Viki
    -0.58
    antity
    -0.57
    koop
    -0.57
    centration
    -0.57
    didReceive
    -0.57
    POSITIVE LOGITS
    </em>
    1.36
    </u>
    1.14
    </strong>
    1.09
    </i>
    1.04
    </h5>
    1.00
    </code>
    0.91
    </s>
    0.90
    </h4>
    0.89
    </h6>
    0.87
    </h2>
    0.85
    Activations Density 0.204%

    No Known Activations