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. 2102
    Prev
    Next
    INDEX
    Explanations

    words related to rings or circular objects, as well as musical content

    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
    addContainerGap
    -1.09
    PerformLayout
    -0.93
    routeProvider
    -0.93
    脚注の使い方
    -0.89
    存于互联网档案馆
    -0.84
    __*/
    -0.82
    bebasan
    -0.82
     tramonto
    -0.81
    QMetaType
    -0.81
    Filmografie
    -0.80
    POSITIVE LOGITS
    ng
    1.05
    ang
    1.01
    ong
    0.99
    Ing
    0.96
    pong
    0.94
     Ing
    0.93
    ANG
    0.93
    ONG
    0.90
     ING
    0.90
    ung
    0.89
    Activations Density 0.142%

    No Known Activations