© 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-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14573
    Prev
    Next
    INDEX
    Explanations

    components of source code for Java applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.63
     Photocase
    -0.59
     autorytatywna
    -0.58
     CreateTagHelper
    -0.54
     فريبيس
    -0.54
    GEBURTSDATUM
    -0.54
    ьаж
    -0.53
     estekak
    -0.52
     BoxFit
    -0.52
     تضيفلها
    -0.52
    POSITIVE LOGITS
    </em>
    0.47
    </h5>
    0.46
    </h6>
    0.45
    </h3>
    0.45
    </code>
    0.44
    IUrlHelper
    0.44
    </blockquote>
    0.44
    </h2>
    0.43
    </u>
    0.43
    </strong>
    0.42
    Activations Density 0.298%

    No Known Activations