© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 8676
    Prev
    Next
    INDEX
    Explanations

    references to Java documentation and file structure related to software management or programming resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -1.15
    Autoritní
    -1.13
    ########.
    -1.02
     المعيارى
    -0.93
    tagHelperRunner
    -0.92
    AddTagHelper
    -0.90
    parsedMessage
    -0.90
     resourceCulture
    -0.89
    protoimpl
    -0.86
     للاسماء
    -0.86
    POSITIVE LOGITS
    </strong>
    0.38
    </b>
    0.36
     are
    0.35
     include
    0.34
     is
    0.34
    </h2>
    0.34
     includes
    0.33
     http
    0.33
     Seidel
    0.32
    「
    0.32
    Activations Density 0.746%

    No Known Activations