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. 15-GEMMASCOPE-RES-16K
    6. 2121
    Prev
    Next
    INDEX
    Explanations

    references to food and objects associated with culinary themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    gifts and decorations associated with holidays or celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -1.01
    Espèce
    -0.88
    adaptiveStyles
    -0.82
     فريبيس
    -0.82
    Personendaten
    -0.76
    ReusableCell
    -0.75
     useParams
    -0.74
     Normdatei
    -0.74
     propOrder
    -0.73
    SqlClient
    -0.71
    POSITIVE LOGITS
    riks
    0.46
    пали
    0.46
     Young
    0.45
     Naciones
    0.44
     изобра
    0.44
    女性の
    0.44
    usión
    0.43
    Young
    0.42
    옴
    0.42
    様子
    0.42
    Activations Density 0.214%

    No Known Activations