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. 2-GEMMASCOPE-RES-16K
    6. 15184
    Prev
    Next
    INDEX
    Explanations

    keywords and components related to Android UI layout and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndContext
    -0.65
     مشين
    -0.59
     Prey
    -0.58
    ImageContext
    -0.55
    Hozzáférés
    -0.54
    日閲覧
    -0.53
     تضيفلها
    -0.52
    GEBURTSDATUM
    -0.51
    idiv
    -0.51
     Vys
    -0.50
    POSITIVE LOGITS
     transfieras
    0.67
    tonode
    0.62
    glDelete
    0.55
    談社
    0.55
    CardHeader
    0.53
     cuantos
    0.53
    varande
    0.51
    ItemBackground
    0.51
    ∓
    0.50
    ophil
    0.49
    Activations Density 0.171%

    No Known Activations