Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6807
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions related to social media activity, particularly Instagram

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AllAfrica
    -0.48
    WithMany
    -0.47
     ब्रेकडाउन
    -0.46
     مشين
    -0.45
    侍
    -0.44
    onAttach
    -0.43
     Carp
    -0.43
    forChild
    -0.43
    alone
    -0.42
     Computing
    -0.42
    POSITIVE LOGITS
     Instagram
    0.82
     instagram
    0.74
    Instagram
    0.71
     INSTAGRAM
    0.64
    instagram
    0.62
     اینستاگرام
    0.54
    ConstraintMaker
    0.54
    INSTAGRAM
    0.53
     insta
    0.48
     kvä
    0.44
    Activations Density 0.039%

    No Known Activations