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. 7-GEMMASCOPE-RES-16K
    6. 6590
    Prev
    Next
    INDEX
    Explanations

    references to various types of magazines and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -1.13
     AssemblyCulture
    -1.11
    awtextra
    -1.09
     Савезне
    -1.06
    AndEndTag
    -0.99
    InjectAttribute
    -0.98
    MergeFrom
    -0.92
    UnusedPrivate
    -0.91
     unknownFields
    -0.90
    +#+#
    -0.87
    POSITIVE LOGITS
     app
    0.86
     magazine
    0.77
     website
    0.72
     apps
    0.69
     podcast
    0.69
     program
    0.67
     websites
    0.64
     App
    0.63
    App
    0.61
     magazines
    0.58
    Activations Density 0.242%

    No Known Activations